Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3232. Min Range: -6.3232
Max Act: 6.2920. Min Act: -0.1700
Data Index: 5676048 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3232. Min Range: -6.3232
Max Act: 6.3232. Min Act: -0.1700
Data Index: 6676267 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.9482. Min Act: -0.1700
Data Index: 7443057 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.8545. Min Act: -0.1700
Data Index: 5868830 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.8545. Min Act: -0.1700
Data Index: 1159427 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.8232. Min Act: -0.1700
Data Index: 734233 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.8232. Min Act: -0.1700
Data Index: 7079251 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.8232. Min Act: -0.1700
Data Index: 4166612 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.7920. Min Act: -0.1700
Data Index: 7841035 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.7295. Min Act: -0.1700
Data Index: 452766 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6670. Min Act: -0.1700
Data Index: 4343005 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6982. Min Act: -0.1700
Data Index: 75808 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6670. Min Act: -0.1700
Data Index: 8607189 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6357. Min Act: -0.1700
Data Index: 5734657 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6357. Min Act: -0.1700
Data Index: 1181813 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6670. Min Act: -0.1700
Data Index: 4645995 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 6385746 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 4962651 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 6280889 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3232. Min Range: -6.3232
Max Act: 5.6045. Min Act: -0.1700
Data Index: 2244668 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19