Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.5786. Min Act: -0.1700
Data Index: 4834754 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.3286. Min Act: -0.1700
Data Index: 6904591 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.1411. Min Act: -0.1700
Data Index: 4566057 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.0786. Min Act: -0.1700
Data Index: 4154125 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.0786. Min Act: -0.1700
Data Index: 182452 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5786. Min Range: -9.5786
Max Act: 9.0161. Min Act: -0.1700
Data Index: 6365347 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.9536. Min Act: -0.1700
Data Index: 7134494 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.9536. Min Act: -0.1700
Data Index: 7690398 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.9536. Min Act: -0.1700
Data Index: 3603176 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8911. Min Act: -0.1700
Data Index: 1545082 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8911. Min Act: -0.1700
Data Index: 6337185 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8911. Min Act: -0.1700
Data Index: 8021994 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 5235343 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 6373964 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 5115186 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.7661. Min Act: -0.1700
Data Index: 7681469 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 2185565 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 6652625 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 1853215 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5786. Min Range: -9.5786
Max Act: 8.8286. Min Act: -0.1700
Data Index: 2186732 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19