Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.9337. Min Act: -0.1700
Data Index: 1986857 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.4337. Min Act: -0.1700
Data Index: 7117986 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.3712. Min Act: -0.1700
Data Index: 2464978 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.3712. Min Act: -0.1700
Data Index: 3049548 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.1212. Min Act: -0.1700
Data Index: 4264968 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.0587. Min Act: -0.1700
Data Index: 7303285 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.0587. Min Act: -0.1700
Data Index: 4264964 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9337. Min Range: -8.9337
Max Act: 8.0274. Min Act: -0.1700
Data Index: 4169629 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.9649. Min Act: -0.1700
Data Index: 4188627 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.9024. Min Act: -0.1700
Data Index: 915428 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.9024. Min Act: -0.1700
Data Index: 6301654 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.8712. Min Act: -0.1700
Data Index: 6619650 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.8712. Min Act: -0.1700
Data Index: 5839076 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7462. Min Act: -0.1700
Data Index: 2098925 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7774. Min Act: -0.1700
Data Index: 4022007 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7774. Min Act: -0.1700
Data Index: 1725948 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7149. Min Act: -0.1700
Data Index: 328817 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7149. Min Act: -0.1700
Data Index: 3101784 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7149. Min Act: -0.1700
Data Index: 3088763 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9337. Min Range: -8.9337
Max Act: 7.7149. Min Act: -0.1700
Data Index: 3969532 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19