Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 173 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.8594. Min Act: -0.1700
Data Index: 4276747 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.8907. Min Act: -0.1700
Data Index: 5432511 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.3282. Min Act: -0.1700
Data Index: 7037070 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.2969. Min Act: -0.1700
Data Index: 7579545 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.1719. Min Act: -0.1700
Data Index: 2611739 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0782. Min Act: -0.1700
Data Index: 3277837 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.1407. Min Act: -0.1700
Data Index: 7984559 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0469. Min Act: -0.1700
Data Index: 4615626 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0469. Min Act: -0.1700
Data Index: 1194097 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0469. Min Act: -0.1700
Data Index: 4344909 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0157. Min Act: -0.1700
Data Index: 1877259 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0157. Min Act: -0.1700
Data Index: 5689756 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0469. Min Act: -0.1700
Data Index: 6903935 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8313111 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0469. Min Act: -0.1700
Data Index: 4615625 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.9532. Min Act: -0.1700
Data Index: 1903310 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8907. Min Range: -7.8907
Max Act: 7.0157. Min Act: -0.1700
Data Index: 4182452 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.9532. Min Act: -0.1700
Data Index: 1194098 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.9532. Min Act: -0.1700
Data Index: 4156448 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8907. Min Range: -7.8907
Max Act: 6.9219. Min Act: -0.1700
Data Index: 4976413 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19