Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6038 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.7303. Min Act: -0.1700
Data Index: 3397267 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.7147. Min Act: -0.1700
Data Index: 3679210 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6990. Min Act: -0.1700
Data Index: 4421734 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6677. Min Act: -0.1700
Data Index: 611347 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6521. Min Act: -0.1700
Data Index: 3940896 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6677. Min Act: -0.1700
Data Index: 8019411 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6521. Min Act: -0.1700
Data Index: 1142015 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6521. Min Act: -0.1700
Data Index: 2053351 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6364. Min Act: -0.1700
Data Index: 5932910 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6364. Min Act: -0.1700
Data Index: 1285898 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6364. Min Act: -0.1700
Data Index: 3427112 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 1610337 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 140392 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 6272467 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 5698684 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6051. Min Act: -0.1700
Data Index: 2339207 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2902408 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.5895. Min Act: -0.1700
Data Index: 8010318 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.5895. Min Act: -0.1700
Data Index: 2999946 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7303. Min Range: -3.7303
Max Act: 3.6208. Min Act: -0.1700
Data Index: 5403293 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19