Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.7469. Min Act: -0.1700
Data Index: 3210841 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.6844. Min Act: -0.1700
Data Index: 3754943 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.6219. Min Act: -0.1700
Data Index: 4207111 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.5594. Min Act: -0.1700
Data Index: 6794242 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.5281. Min Act: -0.1700
Data Index: 2513761 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4969. Min Act: -0.1700
Data Index: 4800252 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4969. Min Act: -0.1700
Data Index: 8369893 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4344. Min Act: -0.1700
Data Index: 8382325 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4344. Min Act: -0.1700
Data Index: 6688651 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4031. Min Act: -0.1700
Data Index: 4965779 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4031. Min Act: -0.1700
Data Index: 2513759 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 4367389 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 7648100 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2781. Min Act: -0.1700
Data Index: 2020769 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3094. Min Act: -0.1700
Data Index: 6794241 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2781. Min Act: -0.1700
Data Index: 3736756 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2469. Min Act: -0.1700
Data Index: 5862733 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2469. Min Act: -0.1700
Data Index: 8256165 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2781. Min Act: -0.1700
Data Index: 3162864 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2156. Min Act: -0.1700
Data Index: 7249266 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19