Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.2810. Min Act: -0.1700
Data Index: 7012347 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.1873. Min Act: -0.1700
Data Index: 1439769 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.1560. Min Act: -0.1700
Data Index: 54352 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.1248. Min Act: -0.1700
Data Index: 304063 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.1248. Min Act: -0.1700
Data Index: 7410459 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.9998. Min Act: -0.1700
Data Index: 6386838 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2810. Min Range: -7.2810
Max Act: 7.0310. Min Act: -0.1700
Data Index: 5122948 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.9373. Min Act: -0.1700
Data Index: 7035383 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4471422 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8748. Min Act: -0.1700
Data Index: 8049105 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8748. Min Act: -0.1700
Data Index: 6185311 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8748. Min Act: -0.1700
Data Index: 3904642 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8748. Min Act: -0.1700
Data Index: 5445218 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4686717 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8123. Min Act: -0.1700
Data Index: 3108552 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8435. Min Act: -0.1700
Data Index: 8232522 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8123. Min Act: -0.1700
Data Index: 2169409 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8123. Min Act: -0.1700
Data Index: 2019768 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8123. Min Act: -0.1700
Data Index: 7094167 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2810. Min Range: -7.2810
Max Act: 6.8123. Min Act: -0.1700
Data Index: 1018570 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19