Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.6896. Min Act: -0.1700
Data Index: 1955706 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.5959. Min Act: -0.1700
Data Index: 4406091 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1896. Min Act: -0.1700
Data Index: 5882237 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.2209. Min Act: -0.1700
Data Index: 2320703 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.1271. Min Act: -0.1700
Data Index: 6677728 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0959. Min Act: -0.1700
Data Index: 6527444 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0646. Min Act: -0.1700
Data Index: 233061 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0334. Min Act: -0.1700
Data Index: 4910288 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0334. Min Act: -0.1700
Data Index: 8623741 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6896. Min Range: -7.6896
Max Act: 7.0021. Min Act: -0.1700
Data Index: 5231898 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.9396. Min Act: -0.1700
Data Index: 7435348 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.9084. Min Act: -0.1700
Data Index: 8344461 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.9084. Min Act: -0.1700
Data Index: 2427882 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.9084. Min Act: -0.1700
Data Index: 7375370 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8771. Min Act: -0.1700
Data Index: 713919 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8771. Min Act: -0.1700
Data Index: 3498876 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8459. Min Act: -0.1700
Data Index: 1556959 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8771. Min Act: -0.1700
Data Index: 4406087 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8459. Min Act: -0.1700
Data Index: 1803212 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6896. Min Range: -7.6896
Max Act: 6.8459. Min Act: -0.1700
Data Index: 5586708 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19