Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5952 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1205. Min Range: -8.1205
Max Act: 8.1205. Min Act: -0.1700
Data Index: 2974457 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 1429162 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1205. Min Range: -8.1205
Max Act: 8.0267. Min Act: -0.1700
Data Index: 2331030 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1205. Min Range: -8.1205
Max Act: 8.0267. Min Act: -0.1700
Data Index: 854249 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9642. Min Act: -0.1700
Data Index: 6806903 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9955. Min Act: -0.1700
Data Index: 229600 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9642. Min Act: -0.1700
Data Index: 5715608 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9017. Min Act: -0.1700
Data Index: 121760 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9330. Min Act: -0.1700
Data Index: 121761 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9017. Min Act: -0.1700
Data Index: 5050991 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9017. Min Act: -0.1700
Data Index: 568051 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.9017. Min Act: -0.1700
Data Index: 496569 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8392. Min Act: -0.1700
Data Index: 4631849 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8392. Min Act: -0.1700
Data Index: 6994347 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8705. Min Act: -0.1700
Data Index: 7595681 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8705. Min Act: -0.1700
Data Index: 1545174 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8392. Min Act: -0.1700
Data Index: 2504806 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8392. Min Act: -0.1700
Data Index: 2504802 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8705. Min Act: -0.1700
Data Index: 6966241 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1205. Min Range: -8.1205
Max Act: 7.8392. Min Act: -0.1700
Data Index: 78940 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19