Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5804. Min Range: -5.5804
Max Act: 5.5804. Min Act: -0.1700
Data Index: 3457405 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5804. Min Range: -5.5804
Max Act: 5.2054. Min Act: -0.1700
Data Index: 6938884 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.9867. Min Act: -0.1700
Data Index: 7051458 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.9554. Min Act: -0.1700
Data Index: 617613 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.9554. Min Act: -0.1700
Data Index: 3149494 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.9554. Min Act: -0.1700
Data Index: 507498 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.9242. Min Act: -0.1700
Data Index: 6857361 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8929. Min Act: -0.1700
Data Index: 8081886 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 4802181 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8617. Min Act: -0.1700
Data Index: 6479991 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8617. Min Act: -0.1700
Data Index: 6156800 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8617. Min Act: -0.1700
Data Index: 7363545 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 6573457 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 7094197 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 7511749 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 8797800 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.8617. Min Act: -0.1700
Data Index: 1839274 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 206317 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 5340939 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5804. Min Range: -5.5804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 6334548 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19