Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1554635 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.7040. Min Act: -0.1700
Data Index: 4921805 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.6728. Min Act: -0.1700
Data Index: 7297365 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.5790. Min Act: -0.1700
Data Index: 5646344 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.5478. Min Act: -0.1700
Data Index: 2772686 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.5478. Min Act: -0.1700
Data Index: 2511400 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.4853. Min Act: -0.1700
Data Index: 4719878 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.4540. Min Act: -0.1700
Data Index: 1053404 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.4228. Min Act: -0.1700
Data Index: 3578874 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.4228. Min Act: -0.1700
Data Index: 2276778 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.4228. Min Act: -0.1700
Data Index: 3889163 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3915. Min Act: -0.1700
Data Index: 1360173 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3915. Min Act: -0.1700
Data Index: 4545155 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3603. Min Act: -0.1700
Data Index: 81974 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3603. Min Act: -0.1700
Data Index: 5309940 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3603. Min Act: -0.1700
Data Index: 2398170 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3603. Min Act: -0.1700
Data Index: 2025297 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3290. Min Act: -0.1700
Data Index: 4647746 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3290. Min Act: -0.1700
Data Index: 1192847 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7665. Min Range: -5.7665
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5674612 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19