Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5854 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.9147. Min Act: -0.1700
Data Index: 8695185 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.8834. Min Act: -0.1700
Data Index: 996806 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.7584. Min Act: -0.1700
Data Index: 2385794 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.7272. Min Act: -0.1700
Data Index: 4845335 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.6959. Min Act: -0.1700
Data Index: 3289044 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.7272. Min Act: -0.1700
Data Index: 2814114 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.6647. Min Act: -0.1700
Data Index: 2172398 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.6334. Min Act: -0.1700
Data Index: 1930239 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.6022. Min Act: -0.1700
Data Index: 2602316 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5709. Min Act: -0.1700
Data Index: 5634074 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5709. Min Act: -0.1700
Data Index: 3103105 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5397. Min Act: -0.1700
Data Index: 666629 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5709. Min Act: -0.1700
Data Index: 8788650 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5397. Min Act: -0.1700
Data Index: 4966254 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5397. Min Act: -0.1700
Data Index: 7068837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5084. Min Act: -0.1700
Data Index: 1712976 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5084. Min Act: -0.1700
Data Index: 5578673 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5084. Min Act: -0.1700
Data Index: 4190315 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.5084. Min Act: -0.1700
Data Index: 4008282 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9147. Min Range: -4.9147
Max Act: 4.4772. Min Act: -0.1700
Data Index: 8137264 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19