Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.4605. Min Act: -0.1700
Data Index: 7563405 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.3980. Min Act: -0.1700
Data Index: 6334329 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.3667. Min Act: -0.1700
Data Index: 3122300 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.2105. Min Act: -0.1700
Data Index: 8053975 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1480. Min Act: -0.1700
Data Index: 4771381 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1480. Min Act: -0.1700
Data Index: 4352938 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1423382 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1167. Min Act: -0.1700
Data Index: 4070459 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 1242389 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1755150 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 2105753 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.1167. Min Act: -0.1700
Data Index: 4257305 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 6946138 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 4747024 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 1243580 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0855. Min Act: -0.1700
Data Index: 985402 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0542. Min Act: -0.1700
Data Index: 571286 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0542. Min Act: -0.1700
Data Index: 558567 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0542. Min Act: -0.1700
Data Index: 4641482 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4605. Min Range: -6.4605
Max Act: 6.0542. Min Act: -0.1700
Data Index: 6280577 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19