Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.5479. Min Act: -0.1700
Data Index: 7642636 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.5166. Min Act: -0.1700
Data Index: 697812 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.4229. Min Act: -0.1700
Data Index: 5966279 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.3291. Min Act: -0.1700
Data Index: 3751407 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.3604. Min Act: -0.1700
Data Index: 7774046 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.3604. Min Act: -0.1700
Data Index: 122468 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2979. Min Act: -0.1700
Data Index: 3157813 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2666. Min Act: -0.1700
Data Index: 2057225 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2666. Min Act: -0.1700
Data Index: 7442628 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2666. Min Act: -0.1700
Data Index: 2390080 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2041. Min Act: -0.1700
Data Index: 8787752 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2041. Min Act: -0.1700
Data Index: 8752427 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 5546837 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 6597121 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 5819111 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 2281655 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 166786 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 2048249 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.2041. Min Act: -0.1700
Data Index: 1921425 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5479. Min Range: -6.5479
Max Act: 6.1729. Min Act: -0.1700
Data Index: 3109002 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19