Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2084. Min Range: -6.2084
Max Act: 6.2084. Min Act: -0.1700
Data Index: 5869419 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.8959. Min Act: -0.1700
Data Index: 5464321 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.8334. Min Act: -0.1700
Data Index: 5022101 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.8334. Min Act: -0.1700
Data Index: 8144843 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.8022. Min Act: -0.1700
Data Index: 5868884 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7064130 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7709. Min Act: -0.1700
Data Index: 7246042 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7397. Min Act: -0.1700
Data Index: 233446 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5169044 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7397. Min Act: -0.1700
Data Index: 4202207 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6772. Min Act: -0.1700
Data Index: 3236703 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6772. Min Act: -0.1700
Data Index: 129591 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7397. Min Act: -0.1700
Data Index: 5747149 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.7397. Min Act: -0.1700
Data Index: 4508857 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6772. Min Act: -0.1700
Data Index: 6117322 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6772. Min Act: -0.1700
Data Index: 5169039 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6147. Min Act: -0.1700
Data Index: 2094093 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2617861 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6459. Min Act: -0.1700
Data Index: 4566224 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2084. Min Range: -6.2084
Max Act: 5.6459. Min Act: -0.1700
Data Index: 585925 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19