Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.9475. Min Act: -0.1700
Data Index: 6980082 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.9163. Min Act: -0.1700
Data Index: 1173245 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.9163. Min Act: -0.1700
Data Index: 363170 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.9163. Min Act: -0.1700
Data Index: 1969923 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8850. Min Act: -0.1700
Data Index: 1918233 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8850. Min Act: -0.1700
Data Index: 279473 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4618307 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8850. Min Act: -0.1700
Data Index: 4092127 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 2582524 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6226415 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 180436 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 8614981 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 5365963 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6402343 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8225. Min Act: -0.1700
Data Index: 8756359 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.7913. Min Act: -0.1700
Data Index: 679810 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8225. Min Act: -0.1700
Data Index: 4013102 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8225. Min Act: -0.1700
Data Index: 3942363 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.8225. Min Act: -0.1700
Data Index: 6201779 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9475. Min Range: -4.9475
Max Act: 4.7913. Min Act: -0.1700
Data Index: 291049 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19