Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.2479. Min Act: -0.1700
Data Index: 2930125 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0291. Min Act: -0.1700
Data Index: 4453828 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2479. Min Range: -6.2479
Max Act: 6.0604. Min Act: -0.1700
Data Index: 8254591 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9354. Min Act: -0.1700
Data Index: 628316 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.9041. Min Act: -0.1700
Data Index: 3595441 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8729. Min Act: -0.1700
Data Index: 6846712 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8729. Min Act: -0.1700
Data Index: 1765073 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8416. Min Act: -0.1700
Data Index: 5473563 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8416. Min Act: -0.1700
Data Index: 1637063 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8416. Min Act: -0.1700
Data Index: 998659 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 8690771 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.8104. Min Act: -0.1700
Data Index: 5223008 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5762921 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6958718 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7479. Min Act: -0.1700
Data Index: 4344501 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7166. Min Act: -0.1700
Data Index: 2733958 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7479. Min Act: -0.1700
Data Index: 8107200 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7166. Min Act: -0.1700
Data Index: 8065432 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.7166. Min Act: -0.1700
Data Index: 4667576 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2479. Min Range: -6.2479
Max Act: 5.6854. Min Act: -0.1700
Data Index: 234111 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19