Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 2207045 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7225. Min Act: -0.1700
Data Index: 3399899 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 8677962 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4413. Min Act: -0.1700
Data Index: 855834 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4413. Min Act: -0.1700
Data Index: 654527 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.3163. Min Act: -0.1700
Data Index: 6863450 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3451269 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 6208301 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1600. Min Act: -0.1700
Data Index: 2673589 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 8363585 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 4159925 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1600. Min Act: -0.1700
Data Index: 2635160 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 7995217 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 7862387 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 1047427 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.1288. Min Act: -0.1700
Data Index: 2901823 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 4178580 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.0975. Min Act: -0.1700
Data Index: 4645552 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 3562068 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.0975. Min Act: -0.1700
Data Index: 7904577 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19