Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.9400. Min Act: -0.1700
Data Index: 1323869 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.9400. Min Act: -0.1700
Data Index: 5825400 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.8931. Min Act: -0.1700
Data Index: 5467959 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1675420 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.8775. Min Act: -0.1700
Data Index: 8568069 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.8619. Min Act: -0.1700
Data Index: 1320868 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.8150. Min Act: -0.1700
Data Index: 8230903 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7993. Min Act: -0.1700
Data Index: 1934072 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7837. Min Act: -0.1700
Data Index: 4670260 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7837. Min Act: -0.1700
Data Index: 1620377 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7211. Min Act: -0.1700
Data Index: 3450549 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7211. Min Act: -0.1700
Data Index: 1670297 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7055. Min Act: -0.1700
Data Index: 1763524 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.7211. Min Act: -0.1700
Data Index: 1828661 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6898. Min Act: -0.1700
Data Index: 762433 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6742. Min Act: -0.1700
Data Index: 6981934 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6898. Min Act: -0.1700
Data Index: 3183332 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6742. Min Act: -0.1700
Data Index: 8082798 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6585. Min Act: -0.1700
Data Index: 331553 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9400. Min Range: -3.9400
Max Act: 3.6429. Min Act: -0.1700
Data Index: 2816988 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19