Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.6342. Min Act: -0.1700
Data Index: 7779545 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.6342. Min Act: -0.1700
Data Index: 3041707 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.6342. Min Act: -0.1700
Data Index: 1038448 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.6342. Min Act: -0.1700
Data Index: 3058192 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5717. Min Act: -0.1700
Data Index: 6813610 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5717. Min Act: -0.1700
Data Index: 4723967 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5717. Min Act: -0.1700
Data Index: 3041705 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5717. Min Act: -0.1700
Data Index: 7451948 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 6455951 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5405. Min Act: -0.1700
Data Index: 3392654 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5405. Min Act: -0.1700
Data Index: 2441549 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 3041706 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 1459524 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5405. Min Act: -0.1700
Data Index: 3041708 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 5767285 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 505331 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 3500318 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.4780. Min Act: -0.1700
Data Index: 3917641 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 1603021 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6342. Min Range: -4.6342
Max Act: 4.5092. Min Act: -0.1700
Data Index: 4995970 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19