Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.8576. Min Act: -0.1700
Data Index: 7256016 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.7326. Min Act: -0.1700
Data Index: 5893834 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.7326. Min Act: -0.1700
Data Index: 5513992 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.7013. Min Act: -0.1700
Data Index: 4704604 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.6701. Min Act: -0.1700
Data Index: 731412 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.6388. Min Act: -0.1700
Data Index: 6679083 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.6388. Min Act: -0.1700
Data Index: 8190228 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.5763. Min Act: -0.1700
Data Index: 1289093 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.5763. Min Act: -0.1700
Data Index: 1099175 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.5138. Min Act: -0.1700
Data Index: 3467475 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4826. Min Act: -0.1700
Data Index: 1538898 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.5138. Min Act: -0.1700
Data Index: 8333855 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7530279 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4826. Min Act: -0.1700
Data Index: 4779983 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7620828 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4513. Min Act: -0.1700
Data Index: 806252 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.4201. Min Act: -0.1700
Data Index: 6061352 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.3888. Min Act: -0.1700
Data Index: 8585697 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.3888. Min Act: -0.1700
Data Index: 6165740 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8576. Min Range: -6.8576
Max Act: 6.3576. Min Act: -0.1700
Data Index: 1677701 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19