Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.5954. Min Act: -0.1700
Data Index: 6809345 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.5641. Min Act: -0.1700
Data Index: 4722275 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.3454. Min Act: -0.1700
Data Index: 6534600 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.3141. Min Act: -0.1700
Data Index: 5437557 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.2204. Min Act: -0.1700
Data Index: 447940 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.2204. Min Act: -0.1700
Data Index: 7688052 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.2204. Min Act: -0.1700
Data Index: 6284753 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.1579. Min Act: -0.1700
Data Index: 2506260 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.1579. Min Act: -0.1700
Data Index: 2577290 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.0329. Min Act: -0.1700
Data Index: 2467714 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.0329. Min Act: -0.1700
Data Index: 2690206 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.0016. Min Act: -0.1700
Data Index: 7990917 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5954. Min Range: -7.5954
Max Act: 7.0016. Min Act: -0.1700
Data Index: 1709928 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9704. Min Act: -0.1700
Data Index: 4631331 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9704. Min Act: -0.1700
Data Index: 4029133 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 2369749 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 3345027 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 1679037 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 7399649 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5954. Min Range: -7.5954
Max Act: 6.9391. Min Act: -0.1700
Data Index: 5852258 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19