Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5950 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.5111. Min Act: -0.1700
Data Index: 2778313 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.4798. Min Act: -0.1700
Data Index: 4514270 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.3548. Min Act: -0.1700
Data Index: 863308 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.3548. Min Act: -0.1700
Data Index: 6593060 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.3236. Min Act: -0.1700
Data Index: 3247362 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2923. Min Act: -0.1700
Data Index: 7706152 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2923. Min Act: -0.1700
Data Index: 3702452 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2923. Min Act: -0.1700
Data Index: 142048 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2611. Min Act: -0.1700
Data Index: 100942 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2611. Min Act: -0.1700
Data Index: 4588238 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2611. Min Act: -0.1700
Data Index: 1473935 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2298. Min Act: -0.1700
Data Index: 1261751 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.2298. Min Act: -0.1700
Data Index: 8689880 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1986. Min Act: -0.1700
Data Index: 4742968 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1673. Min Act: -0.1700
Data Index: 8105841 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1673. Min Act: -0.1700
Data Index: 2493785 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1361. Min Act: -0.1700
Data Index: 1642478 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1361. Min Act: -0.1700
Data Index: 7686759 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.1048. Min Act: -0.1700
Data Index: 542937 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5111. Min Range: -7.5111
Max Act: 7.0736. Min Act: -0.1700
Data Index: 4668748 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19