Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.8331. Min Act: -0.1700
Data Index: 7265276 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.7706. Min Act: -0.1700
Data Index: 7247719 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.6456. Min Act: -0.1700
Data Index: 4611960 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.6143. Min Act: -0.1700
Data Index: 230607 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5831. Min Act: -0.1700
Data Index: 1116918 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.6143. Min Act: -0.1700
Data Index: 4024536 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5831. Min Act: -0.1700
Data Index: 855684 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 6360695 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.4893. Min Act: -0.1700
Data Index: 4762330 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5518. Min Act: -0.1700
Data Index: 890650 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 2739928 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 3630834 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5518. Min Act: -0.1700
Data Index: 2815603 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 2726903 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.4893. Min Act: -0.1700
Data Index: 5977902 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5518. Min Act: -0.1700
Data Index: 4803797 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 7245727 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.5206. Min Act: -0.1700
Data Index: 4593217 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.4893. Min Act: -0.1700
Data Index: 2460826 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8331. Min Range: -4.8331
Max Act: 4.4581. Min Act: -0.1700
Data Index: 4839993 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19