Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 610 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4948217 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7662601 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8783. Min Act: -0.1700
Data Index: 5016292 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.9096. Min Act: -0.1700
Data Index: 5990093 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8783. Min Act: -0.1700
Data Index: 7233326 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8783. Min Act: -0.1700
Data Index: 81878 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.8471. Min Act: -0.1700
Data Index: 7262392 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.7846. Min Act: -0.1700
Data Index: 1528789 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.7533. Min Act: -0.1700
Data Index: 696813 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.7221. Min Act: -0.1700
Data Index: 7731940 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.7221. Min Act: -0.1700
Data Index: 8660827 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.7221. Min Act: -0.1700
Data Index: 402954 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.6596. Min Act: -0.1700
Data Index: 3602937 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.6596. Min Act: -0.1700
Data Index: 4851316 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.6283. Min Act: -0.1700
Data Index: 5742732 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7611044 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 2624685 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5264921 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 122783 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9096. Min Range: -5.9096
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3451687 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19