Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4333 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.7502. Min Act: -0.1700
Data Index: 7923872 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.7190. Min Act: -0.1700
Data Index: 6620460 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.6252. Min Act: -0.1700
Data Index: 838983 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.6252. Min Act: -0.1700
Data Index: 2389681 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.5940. Min Act: -0.1700
Data Index: 219997 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.5315. Min Act: -0.1700
Data Index: 883597 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.5627. Min Act: -0.1700
Data Index: 7206441 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.5002. Min Act: -0.1700
Data Index: 5929079 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.4377. Min Act: -0.1700
Data Index: 5493705 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.4377. Min Act: -0.1700
Data Index: 789621 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.4065. Min Act: -0.1700
Data Index: 2447626 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.4065. Min Act: -0.1700
Data Index: 4306251 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3752. Min Act: -0.1700
Data Index: 4900006 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3752. Min Act: -0.1700
Data Index: 263724 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3752. Min Act: -0.1700
Data Index: 6457008 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3440. Min Act: -0.1700
Data Index: 2100320 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3440. Min Act: -0.1700
Data Index: 6038494 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3440. Min Act: -0.1700
Data Index: 4046806 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3440. Min Act: -0.1700
Data Index: 997898 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7502. Min Range: -6.7502
Max Act: 6.3440. Min Act: -0.1700
Data Index: 3001231 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19