Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 237 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 19.8388. Min Range: -19.8388
Max Act: 19.8388. Min Act: -0.1700
Data Index: 2573270 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.8388. Min Range: -19.8388
Max Act: 19.8388. Min Act: -0.1700
Data Index: 5109777 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.8388. Min Range: -19.8388
Max Act: 19.7138. Min Act: -0.1700
Data Index: 4731574 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.8388. Min Range: -19.8388
Max Act: 19.5888. Min Act: -0.1700
Data Index: 6563469 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.8388. Min Range: -19.8388
Max Act: 19.2138. Min Act: -0.1700
Data Index: 1454343 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.8388. Min Range: -19.8388
Max Act: 18.5888. Min Act: -0.1700
Data Index: 781357 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.8388. Min Range: -19.8388
Max Act: 18.9638. Min Act: -0.1700
Data Index: 4651862 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.8388. Min Range: -19.8388
Max Act: 18.9638. Min Act: -0.1700
Data Index: 7918590 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.8388. Min Range: -19.8388
Max Act: 18.4638. Min Act: -0.1700
Data Index: 2161896 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.8388. Min Range: -19.8388
Max Act: 18.2138. Min Act: -0.1700
Data Index: 7373435 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.8388. Min Act: -0.1700
Data Index: 3633077 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.8388. Min Act: -0.1700
Data Index: 3019617 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.7138. Min Act: -0.1700
Data Index: 8329126 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.7138. Min Act: -0.1700
Data Index: 8700356 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.5888. Min Act: -0.1700
Data Index: 1770086 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.5888. Min Act: -0.1700
Data Index: 3126649 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.5888. Min Act: -0.1700
Data Index: 8445586 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.5888. Min Act: -0.1700
Data Index: 8379408 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.3388. Min Act: -0.1700
Data Index: 4708204 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.8388. Min Range: -19.8388
Max Act: 17.3388. Min Act: -0.1700
Data Index: 742989 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19