Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0445. Min Range: -6.0445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 2440706 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0445. Min Range: -6.0445
Max Act: 6.0445. Min Act: -0.1700
Data Index: 942926 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.9195. Min Act: -0.1700
Data Index: 6872119 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.7633. Min Act: -0.1700
Data Index: 8719675 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.7008. Min Act: -0.1700
Data Index: 6688661 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4967444 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.7008. Min Act: -0.1700
Data Index: 7797945 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6695. Min Act: -0.1700
Data Index: 4480371 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6695. Min Act: -0.1700
Data Index: 1150727 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7354782 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5478877 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 2796433 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 1747200 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 1576227 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 2836795 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6881214 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 2288425 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 201547 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 8077044 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0445. Min Range: -6.0445
Max Act: 5.6383. Min Act: -0.1700
Data Index: 3521284 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19