Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1895 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.8819. Min Act: -0.1700
Data Index: 84797 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.6944. Min Act: -0.1700
Data Index: 621098 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.6631. Min Act: -0.1700
Data Index: 4367034 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.6006. Min Act: -0.1700
Data Index: 3478493 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.6006. Min Act: -0.1700
Data Index: 4447724 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.5069. Min Act: -0.1700
Data Index: 3090988 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4756. Min Act: -0.1700
Data Index: 5073767 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4756. Min Act: -0.1700
Data Index: 3837525 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4756. Min Act: -0.1700
Data Index: 188911 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4444. Min Act: -0.1700
Data Index: 3056637 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4756. Min Act: -0.1700
Data Index: 7526367 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4131. Min Act: -0.1700
Data Index: 439109 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.4131. Min Act: -0.1700
Data Index: 1237990 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.3819. Min Act: -0.1700
Data Index: 7787448 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.3819. Min Act: -0.1700
Data Index: 5153272 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.3194. Min Act: -0.1700
Data Index: 5557737 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.3506. Min Act: -0.1700
Data Index: 932459 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.2881. Min Act: -0.1700
Data Index: 5705669 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.2881. Min Act: -0.1700
Data Index: 7274954 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8819. Min Range: -6.8819
Max Act: 6.2881. Min Act: -0.1700
Data Index: 5390244 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19