Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.9728. Min Act: -0.1700
Data Index: 3038677 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.8321. Min Act: -0.1700
Data Index: 268889 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7852. Min Act: -0.1700
Data Index: 1181321 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7852. Min Act: -0.1700
Data Index: 8348470 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7852. Min Act: -0.1700
Data Index: 3903117 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7696. Min Act: -0.1700
Data Index: 4691037 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7852. Min Act: -0.1700
Data Index: 1804117 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7696. Min Act: -0.1700
Data Index: 3995822 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7539. Min Act: -0.1700
Data Index: 3233990 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7227. Min Act: -0.1700
Data Index: 6512932 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.7070. Min Act: -0.1700
Data Index: 6022102 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6757. Min Act: -0.1700
Data Index: 461969 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6757. Min Act: -0.1700
Data Index: 995163 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6601. Min Act: -0.1700
Data Index: 8045735 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6757. Min Act: -0.1700
Data Index: 6517456 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6601. Min Act: -0.1700
Data Index: 4802422 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6444. Min Act: -0.1700
Data Index: 4422842 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6288. Min Act: -0.1700
Data Index: 1955412 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6131. Min Act: -0.1700
Data Index: 333366 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9728. Min Range: -3.9728
Max Act: 3.6131. Min Act: -0.1700
Data Index: 6535881 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19