Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1617 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0244. Min Range: -1.0244
Max Act: 1.0244. Min Act: -0.1574
Data Index: 1006788 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9897. Min Act: -0.1700
Data Index: 1446121 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9551. Min Act: -0.1500
Data Index: 736861 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9378. Min Act: -0.1700
Data Index: 2740978 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9378. Min Act: -0.1684
Data Index: 2740979 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9378. Min Act: -0.1700
Data Index: 938138 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9207. Min Act: -0.1700
Data Index: 2211260 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9035. Min Act: -0.1700
Data Index: 1622875 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9035. Min Act: -0.1699
Data Index: 4096944 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9035. Min Act: -0.1700
Data Index: 964080 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1699
Data Index: 3589066 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.9035. Min Act: -0.1687
Data Index: 8704140 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1700
Data Index: 1006787 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1699
Data Index: 2740961 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1699
Data Index: 1446120 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1678
Data Index: 6341118 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8864. Min Act: -0.1694
Data Index: 8203059 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8694. Min Act: -0.1700
Data Index: 7381352 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8694. Min Act: -0.1700
Data Index: 7381354 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0244. Min Range: -1.0244
Max Act: 0.8694. Min Act: -0.1700
Data Index: 7978362 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19