Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.8328. Min Act: -0.1700
Data Index: 2106013 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.8016. Min Act: -0.1700
Data Index: 7862900 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.7391. Min Act: -0.1700
Data Index: 143675 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.7703. Min Act: -0.1700
Data Index: 4062867 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.7391. Min Act: -0.1700
Data Index: 3461589 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.7078. Min Act: -0.1700
Data Index: 6006870 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6453. Min Act: -0.1700
Data Index: 2107326 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6453. Min Act: -0.1700
Data Index: 2792313 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6141. Min Act: -0.1700
Data Index: 3724128 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6453. Min Act: -0.1700
Data Index: 6293416 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6453. Min Act: -0.1700
Data Index: 4621069 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6141. Min Act: -0.1700
Data Index: 1116377 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6141. Min Act: -0.1700
Data Index: 2294547 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6141. Min Act: -0.1700
Data Index: 7469133 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.5516. Min Act: -0.1700
Data Index: 8421702 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.6141. Min Act: -0.1700
Data Index: 81859 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.5516. Min Act: -0.1700
Data Index: 5453849 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.5516. Min Act: -0.1700
Data Index: 2878942 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.5203. Min Act: -0.1700
Data Index: 432913 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8328. Min Range: -6.8328
Max Act: 6.4891. Min Act: -0.1700
Data Index: 5571233 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19