Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2170 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5084. Min Range: -7.5084
Max Act: 7.5084. Min Act: -0.1700
Data Index: 6305390 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5084. Min Range: -7.5084
Max Act: 7.1647. Min Act: -0.1700
Data Index: 3814210 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.8834. Min Act: -0.1700
Data Index: 2212674 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.8834. Min Act: -0.1700
Data Index: 3455711 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.8209. Min Act: -0.1700
Data Index: 3642029 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.7584. Min Act: -0.1700
Data Index: 3069051 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.7584. Min Act: -0.1700
Data Index: 1742582 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.6959. Min Act: -0.1700
Data Index: 2599941 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.6959. Min Act: -0.1700
Data Index: 6285470 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.6959. Min Act: -0.1700
Data Index: 6111851 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.6334. Min Act: -0.1700
Data Index: 5725758 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.6334. Min Act: -0.1700
Data Index: 1799120 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5709. Min Act: -0.1700
Data Index: 1421387 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5709. Min Act: -0.1700
Data Index: 7753469 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5709. Min Act: -0.1700
Data Index: 7888604 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5397. Min Act: -0.1700
Data Index: 2411951 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 158532 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 1554049 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 2806415 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5084. Min Range: -7.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 2830210 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19