Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4592 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4959912 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8942. Min Act: -0.1700
Data Index: 1504316 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8942. Min Act: -0.1700
Data Index: 6830105 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8942. Min Act: -0.1700
Data Index: 8793886 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8317. Min Act: -0.1700
Data Index: 5984835 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8004. Min Act: -0.1700
Data Index: 8719456 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.8004. Min Act: -0.1700
Data Index: 7162622 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.6754. Min Act: -0.1700
Data Index: 1494903 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.6442. Min Act: -0.1700
Data Index: 1793809 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3003286 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.6129. Min Act: -0.1700
Data Index: 1270124 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.6129. Min Act: -0.1700
Data Index: 1091569 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5817. Min Act: -0.1700
Data Index: 4039478 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5817. Min Act: -0.1700
Data Index: 5215284 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5817. Min Act: -0.1700
Data Index: 3089949 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5192. Min Act: -0.1700
Data Index: 6310172 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5504. Min Act: -0.1700
Data Index: 1136658 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5192. Min Act: -0.1700
Data Index: 7883597 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.5192. Min Act: -0.1700
Data Index: 6265145 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9254. Min Range: -5.9254
Max Act: 5.4879. Min Act: -0.1700
Data Index: 2232836 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19