Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4025 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1151. Min Range: -6.1151
Max Act: 6.1151. Min Act: -0.1700
Data Index: 1457239 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1151. Min Range: -6.1151
Max Act: 6.0526. Min Act: -0.1700
Data Index: 5966870 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1151. Min Range: -6.1151
Max Act: 6.0526. Min Act: -0.1700
Data Index: 3624276 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1151. Min Range: -6.1151
Max Act: 6.0214. Min Act: -0.1700
Data Index: 905683 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9901. Min Act: -0.1700
Data Index: 2529937 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9589. Min Act: -0.1700
Data Index: 2592080 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9589. Min Act: -0.1700
Data Index: 63040 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9276. Min Act: -0.1700
Data Index: 8634971 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9276. Min Act: -0.1700
Data Index: 7667645 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.9276. Min Act: -0.1700
Data Index: 8379833 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8651. Min Act: -0.1700
Data Index: 5352061 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8339. Min Act: -0.1700
Data Index: 3260650 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8339. Min Act: -0.1700
Data Index: 4924732 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8339. Min Act: -0.1700
Data Index: 4853700 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8339. Min Act: -0.1700
Data Index: 7349934 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.8026. Min Act: -0.1700
Data Index: 3751062 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.7714. Min Act: -0.1700
Data Index: 4267754 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.7714. Min Act: -0.1700
Data Index: 8437898 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.7401. Min Act: -0.1700
Data Index: 6280732 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1151. Min Range: -6.1151
Max Act: 5.7714. Min Act: -0.1700
Data Index: 3682699 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19