Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.6159. Min Act: -0.1700
Data Index: 1250712 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 1976426 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4436. Min Act: -0.1700
Data Index: 3539785 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.4279. Min Act: -0.1700
Data Index: 1827410 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3652. Min Act: -0.1700
Data Index: 2043885 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3809. Min Act: -0.1700
Data Index: 7971342 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3652. Min Act: -0.1700
Data Index: 7995393 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3495. Min Act: -0.1700
Data Index: 3838991 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3495. Min Act: -0.1700
Data Index: 5768161 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3182. Min Act: -0.1700
Data Index: 6543025 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3025. Min Act: -0.1700
Data Index: 3536269 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3025. Min Act: -0.1700
Data Index: 7831794 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.3025. Min Act: -0.1700
Data Index: 8610280 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2868. Min Act: -0.1700
Data Index: 4201510 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2553. Min Act: -0.1700
Data Index: 7659855 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2711. Min Act: -0.1700
Data Index: 5059589 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2553. Min Act: -0.1700
Data Index: 2436767 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2553. Min Act: -0.1700
Data Index: 3626207 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2396. Min Act: -0.1700
Data Index: 6519447 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6159. Min Range: -3.6159
Max Act: 3.2396. Min Act: -0.1700
Data Index: 4145260 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19