Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4901 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.9138. Min Act: -0.1700
Data Index: 7388519 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.7888. Min Act: -0.1700
Data Index: 1354243 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.6013. Min Act: -0.1700
Data Index: 5945108 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.6013. Min Act: -0.1700
Data Index: 369839 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5701. Min Act: -0.1700
Data Index: 5924651 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5388. Min Act: -0.1700
Data Index: 2793395 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5388. Min Act: -0.1700
Data Index: 1617630 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5388. Min Act: -0.1700
Data Index: 1028700 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5388. Min Act: -0.1700
Data Index: 8034771 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5076. Min Act: -0.1700
Data Index: 1545368 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5076. Min Act: -0.1700
Data Index: 6675438 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5076. Min Act: -0.1700
Data Index: 1081254 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5076. Min Act: -0.1700
Data Index: 578393 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.5388. Min Act: -0.1700
Data Index: 6714690 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.4451. Min Act: -0.1700
Data Index: 4269155 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.4451. Min Act: -0.1700
Data Index: 2076504 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.4451. Min Act: -0.1700
Data Index: 2627120 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.4451. Min Act: -0.1700
Data Index: 6036466 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.4138. Min Act: -0.1700
Data Index: 7078912 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9138. Min Range: -5.9138
Max Act: 5.3826. Min Act: -0.1700
Data Index: 382103 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19