Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.3379. Min Act: -0.1700
Data Index: 4264 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.3379. Min Act: -0.1700
Data Index: 6508444 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7952043 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.3379. Min Act: -0.1700
Data Index: 5707806 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.2441. Min Act: -0.1700
Data Index: 7351225 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.2129. Min Act: -0.1700
Data Index: 335436 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.0879. Min Act: -0.1700
Data Index: 7743536 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.0254. Min Act: -0.1700
Data Index: 7036395 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.0254. Min Act: -0.1700
Data Index: 7155478 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3379. Min Range: -5.3379
Max Act: 5.0254. Min Act: -0.1700
Data Index: 5627664 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9941. Min Act: -0.1700
Data Index: 8770498 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9316. Min Act: -0.1700
Data Index: 1498442 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9629. Min Act: -0.1700
Data Index: 3162495 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9316. Min Act: -0.1700
Data Index: 8145858 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9316. Min Act: -0.1700
Data Index: 6441259 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.9004. Min Act: -0.1700
Data Index: 3458778 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.8691. Min Act: -0.1700
Data Index: 2077003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.8691. Min Act: -0.1700
Data Index: 6530287 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.8066. Min Act: -0.1700
Data Index: 2810592 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3379. Min Range: -5.3379
Max Act: 4.8379. Min Act: -0.1700
Data Index: 23260 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19