Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2964. Min Range: -6.2964
Max Act: 6.2964. Min Act: -0.1700
Data Index: 2561182 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2964. Min Range: -6.2964
Max Act: 6.2652. Min Act: -0.1700
Data Index: 7944739 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2964. Min Range: -6.2964
Max Act: 6.0777. Min Act: -0.1700
Data Index: 8568204 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.9839. Min Act: -0.1700
Data Index: 3159921 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.9527. Min Act: -0.1700
Data Index: 6632388 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.9527. Min Act: -0.1700
Data Index: 3310414 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.9214. Min Act: -0.1700
Data Index: 714276 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8902. Min Act: -0.1700
Data Index: 7832035 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8902. Min Act: -0.1700
Data Index: 3734099 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8589. Min Act: -0.1700
Data Index: 7366827 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8902. Min Act: -0.1700
Data Index: 7376343 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8589. Min Act: -0.1700
Data Index: 4889838 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8902. Min Act: -0.1700
Data Index: 2359965 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8902. Min Act: -0.1700
Data Index: 2086564 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.8589. Min Act: -0.1700
Data Index: 2683758 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 3659265 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 1435892 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 3676405 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 77274 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2964. Min Range: -6.2964
Max Act: 5.7964. Min Act: -0.1700
Data Index: 1014641 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19