Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5916 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.1927. Min Act: -0.1700
Data Index: 3297636 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.1927. Min Act: -0.1700
Data Index: 1010834 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6008102 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0677. Min Act: -0.1700
Data Index: 2148719 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 646665 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 2899335 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 2672405 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 1086254 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 1692083 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0989. Min Act: -0.1700
Data Index: 7249496 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0677. Min Act: -0.1700
Data Index: 470875 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0364. Min Act: -0.1700
Data Index: 619259 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0364. Min Act: -0.1700
Data Index: 8068889 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0364. Min Act: -0.1700
Data Index: 5846087 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0364. Min Act: -0.1700
Data Index: 3044775 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0364. Min Act: -0.1700
Data Index: 2979323 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0052. Min Act: -0.1700
Data Index: 3671037 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0052. Min Act: -0.1700
Data Index: 3321625 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0052. Min Act: -0.1700
Data Index: 5249560 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1927. Min Range: -5.1927
Max Act: 5.0052. Min Act: -0.1700
Data Index: 5487564 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19