Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.7455. Min Act: -0.1700
Data Index: 8615485 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.6518. Min Act: -0.1700
Data Index: 6383926 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.6205. Min Act: -0.1700
Data Index: 7730028 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.5893. Min Act: -0.1700
Data Index: 8317105 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.5580. Min Act: -0.1700
Data Index: 7536026 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.4955. Min Act: -0.1700
Data Index: 4776666 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.4955. Min Act: -0.1700
Data Index: 1339354 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.4330. Min Act: -0.1700
Data Index: 8226930 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.4018. Min Act: -0.1700
Data Index: 1666035 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.4330. Min Act: -0.1700
Data Index: 376224 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.3705. Min Act: -0.1700
Data Index: 7616325 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.3393. Min Act: -0.1700
Data Index: 8211425 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.2768. Min Act: -0.1700
Data Index: 7851555 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.2455. Min Act: -0.1700
Data Index: 3210908 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.2455. Min Act: -0.1700
Data Index: 2528974 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.2143. Min Act: -0.1700
Data Index: 3425142 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.1830. Min Act: -0.1700
Data Index: 2446065 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.1830. Min Act: -0.1700
Data Index: 533729 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.1830. Min Act: -0.1700
Data Index: 2644258 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7455. Min Range: -6.7455
Max Act: 6.1518. Min Act: -0.1700
Data Index: 2908130 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19