Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 869 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.6034. Min Act: -0.1700
Data Index: 6381657 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.5409. Min Act: -0.1700
Data Index: 2217019 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.4159. Min Act: -0.1700
Data Index: 2675683 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.2909. Min Act: -0.1700
Data Index: 7321769 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.2909. Min Act: -0.1700
Data Index: 3607406 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.2596. Min Act: -0.1700
Data Index: 4586838 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1971. Min Act: -0.1700
Data Index: 2604534 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1971. Min Act: -0.1700
Data Index: 7599162 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1346. Min Act: -0.1700
Data Index: 7188539 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1659. Min Act: -0.1700
Data Index: 595424 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1659. Min Act: -0.1700
Data Index: 1360777 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1346. Min Act: -0.1700
Data Index: 4979264 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.1034. Min Act: -0.1700
Data Index: 3097449 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.0409. Min Act: -0.1699
Data Index: 8213557 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.0409. Min Act: -0.1700
Data Index: 8349681 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.0721. Min Act: -0.1700
Data Index: 1303677 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.0409. Min Act: -0.1700
Data Index: 8020818 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6034. Min Range: -7.6034
Max Act: 6.9784. Min Act: -0.1700
Data Index: 948336 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6034. Min Range: -7.6034
Max Act: 7.0096. Min Act: -0.1700
Data Index: 1757808 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6034. Min Range: -7.6034
Max Act: 6.9784. Min Act: -0.1700
Data Index: 4711238 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19