Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.9292. Min Act: -0.1700
Data Index: 6114491 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.8667. Min Act: -0.1700
Data Index: 3104134 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.8355. Min Act: -0.1700
Data Index: 83903 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.7730. Min Act: -0.1700
Data Index: 2141343 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.6792. Min Act: -0.1700
Data Index: 4144380 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5855. Min Act: -0.1700
Data Index: 7586334 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5855. Min Act: -0.1700
Data Index: 4596309 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5855. Min Act: -0.1700
Data Index: 7295349 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5542. Min Act: -0.1700
Data Index: 1843187 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5542. Min Act: -0.1700
Data Index: 7353810 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5230. Min Act: -0.1700
Data Index: 6595694 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.5230. Min Act: -0.1700
Data Index: 3425818 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4605. Min Act: -0.1700
Data Index: 5660330 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4605. Min Act: -0.1700
Data Index: 6739501 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4605. Min Act: -0.1700
Data Index: 7524562 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.4605. Min Act: -0.1700
Data Index: 3226687 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3980. Min Act: -0.1700
Data Index: 5307796 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 6324961 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 2645919 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9292. Min Range: -6.9292
Max Act: 6.3667. Min Act: -0.1700
Data Index: 7098031 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19