Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.8375. Min Act: -0.1700
Data Index: 4865490 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.7125. Min Act: -0.1700
Data Index: 3366740 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.6187. Min Act: -0.1700
Data Index: 8223668 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.5875. Min Act: -0.1700
Data Index: 2539169 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.4000. Min Act: -0.1700
Data Index: 4916924 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.2437. Min Act: -0.1700
Data Index: 5373255 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.2125. Min Act: -0.1700
Data Index: 5775006 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.2125. Min Act: -0.1700
Data Index: 3353020 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.2125. Min Act: -0.1700
Data Index: 2545907 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.1812. Min Act: -0.1700
Data Index: 2844452 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.1500. Min Act: -0.1700
Data Index: 3108751 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.1187. Min Act: -0.1700
Data Index: 2306915 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.0875. Min Act: -0.1700
Data Index: 5612487 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8375. Min Range: -7.8375
Max Act: 7.0250. Min Act: -0.1700
Data Index: 1966488 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9937. Min Act: -0.1700
Data Index: 5906149 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9625. Min Act: -0.1700
Data Index: 8526147 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9625. Min Act: -0.1700
Data Index: 1748666 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9625. Min Act: -0.1700
Data Index: 8124738 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9312. Min Act: -0.1700
Data Index: 80433 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8375. Min Range: -7.8375
Max Act: 6.9312. Min Act: -0.1700
Data Index: 3974953 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19