Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.8200. Min Act: -0.1700
Data Index: 2960675 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.6325. Min Act: -0.1700
Data Index: 7785840 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.5075. Min Act: -0.1700
Data Index: 5825126 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.4763. Min Act: -0.1700
Data Index: 6482742 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.2888. Min Act: -0.1700
Data Index: 5042855 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.2575. Min Act: -0.1700
Data Index: 608225 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.2263. Min Act: -0.1700
Data Index: 8439792 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1950. Min Act: -0.1700
Data Index: 6264358 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 8067821 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1950. Min Act: -0.1700
Data Index: 7390333 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 3363663 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 2239383 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 6319691 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 4282674 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1013. Min Act: -0.1700
Data Index: 4256670 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.1325. Min Act: -0.1700
Data Index: 5779829 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.0700. Min Act: -0.1700
Data Index: 8301053 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.0388. Min Act: -0.1700
Data Index: 6706233 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.0700. Min Act: -0.1700
Data Index: 1070123 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8200. Min Range: -7.8200
Max Act: 7.0075. Min Act: -0.1700
Data Index: 3378136 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19