Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3285. Min Range: -7.3285
Max Act: 7.3285. Min Act: -0.1700
Data Index: 2689600 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3285. Min Range: -7.3285
Max Act: 7.0160. Min Act: -0.1700
Data Index: 5852371 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3285. Min Range: -7.3285
Max Act: 7.0472. Min Act: -0.1700
Data Index: 2459262 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3285. Min Range: -7.3285
Max Act: 7.0160. Min Act: -0.1700
Data Index: 1988026 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.9535. Min Act: -0.1700
Data Index: 6188688 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.9535. Min Act: -0.1700
Data Index: 4406714 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.9222. Min Act: -0.1700
Data Index: 7194503 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.8285. Min Act: -0.1700
Data Index: 2249722 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7347. Min Act: -0.1700
Data Index: 2578654 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7660. Min Act: -0.1700
Data Index: 8079087 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7347. Min Act: -0.1700
Data Index: 1578859 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7347. Min Act: -0.1700
Data Index: 340484 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7035. Min Act: -0.1700
Data Index: 339585 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7035. Min Act: -0.1700
Data Index: 1530056 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7035. Min Act: -0.1700
Data Index: 7632171 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.7035. Min Act: -0.1700
Data Index: 8074325 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.6722. Min Act: -0.1700
Data Index: 1391239 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.6410. Min Act: -0.1700
Data Index: 752728 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.6722. Min Act: -0.1700
Data Index: 389551 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3285. Min Range: -7.3285
Max Act: 6.5785. Min Act: -0.1700
Data Index: 7050654 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19