Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.6549. Min Act: -0.1700
Data Index: 3535517 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.4049. Min Act: -0.1700
Data Index: 6253940 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.3424. Min Act: -0.1700
Data Index: 4388549 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.2174. Min Act: -0.1700
Data Index: 5568552 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.2174. Min Act: -0.1700
Data Index: 4961317 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6549. Min Range: -9.6549
Max Act: 9.0299. Min Act: -0.1700
Data Index: 27676 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.9049. Min Act: -0.1700
Data Index: 8554235 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.8424. Min Act: -0.1700
Data Index: 4086249 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.7174. Min Act: -0.1700
Data Index: 3288863 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.6549. Min Act: -0.1700
Data Index: 7696337 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.7174. Min Act: -0.1700
Data Index: 8359024 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.6549. Min Act: -0.1700
Data Index: 3470431 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.6549. Min Act: -0.1700
Data Index: 71823 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 5258204 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.6549. Min Act: -0.1700
Data Index: 486582 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 5546603 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 2202842 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 6289326 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 7364002 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6549. Min Range: -9.6549
Max Act: 8.5924. Min Act: -0.1700
Data Index: 3249144 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19