Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.3295. Min Act: -0.1700
Data Index: 7939179 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.3608. Min Act: -0.1700
Data Index: 7580562 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.2983. Min Act: -0.1700
Data Index: 7160816 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.2358. Min Act: -0.1700
Data Index: 41447 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.1108. Min Act: -0.1700
Data Index: 8771967 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.0795. Min Act: -0.1700
Data Index: 5710718 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.0795. Min Act: -0.1700
Data Index: 3574282 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.0483. Min Act: -0.1700
Data Index: 5827716 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.0483. Min Act: -0.1700
Data Index: 3087477 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3608. Min Range: -7.3608
Max Act: 7.0170. Min Act: -0.1700
Data Index: 5629271 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.8608. Min Act: -0.1700
Data Index: 1657560 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.8295. Min Act: -0.1700
Data Index: 6075081 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7983. Min Act: -0.1700
Data Index: 5585555 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7983. Min Act: -0.1700
Data Index: 6219054 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7358. Min Act: -0.1700
Data Index: 5026934 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7045. Min Act: -0.1700
Data Index: 1237467 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7358. Min Act: -0.1700
Data Index: 6268374 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7045. Min Act: -0.1700
Data Index: 7439550 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7358. Min Act: -0.1700
Data Index: 6149302 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3608. Min Range: -7.3608
Max Act: 6.7358. Min Act: -0.1700
Data Index: 4508594 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19