Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4428 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.3960. Min Act: -0.1700
Data Index: 3839491 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.3335. Min Act: -0.1700
Data Index: 7828732 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.2710. Min Act: -0.1700
Data Index: 1985370 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.2398. Min Act: -0.1700
Data Index: 7425219 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.1773. Min Act: -0.1700
Data Index: 8660133 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.1460. Min Act: -0.1700
Data Index: 4599814 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.1460. Min Act: -0.1700
Data Index: 4678107 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0835. Min Act: -0.1700
Data Index: 8638811 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3358231 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0835. Min Act: -0.1700
Data Index: 6605764 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0523. Min Act: -0.1700
Data Index: 382201 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3475928 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0523. Min Act: -0.1700
Data Index: 4048322 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0835. Min Act: -0.1700
Data Index: 3369628 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0523. Min Act: -0.1700
Data Index: 4668955 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0210. Min Act: -0.1700
Data Index: 3939807 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0210. Min Act: -0.1700
Data Index: 2126250 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0210. Min Act: -0.1700
Data Index: 7861351 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3960. Min Range: -5.3960
Max Act: 5.0210. Min Act: -0.1700
Data Index: 8607740 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3960. Min Range: -5.3960
Max Act: 4.9898. Min Act: -0.1700
Data Index: 34122 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19