Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.7582. Min Act: -0.1700
Data Index: 7336477 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.4457. Min Act: -0.1700
Data Index: 7215582 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.3832. Min Act: -0.1700
Data Index: 2104289 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.2582. Min Act: -0.1700
Data Index: 4681034 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.1957. Min Act: -0.1700
Data Index: 6062507 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.1332. Min Act: -0.1700
Data Index: 4538734 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.1332. Min Act: -0.1700
Data Index: 4282192 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.0707. Min Act: -0.1700
Data Index: 6484889 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7582. Min Range: -10.7582
Max Act: 10.0082. Min Act: -0.1700
Data Index: 5612654 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.9457. Min Act: -0.1700
Data Index: 4906911 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.8832. Min Act: -0.1700
Data Index: 5856448 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.9457. Min Act: -0.1700
Data Index: 2124383 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.8832. Min Act: -0.1700
Data Index: 7276006 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.8832. Min Act: -0.1700
Data Index: 6445370 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.8832. Min Act: -0.1700
Data Index: 7171396 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.7582. Min Act: -0.1700
Data Index: 5322997 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.7582. Min Act: -0.1700
Data Index: 5136276 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.7582. Min Act: -0.1700
Data Index: 2051870 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.7582. Min Act: -0.1700
Data Index: 5636308 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7582. Min Range: -10.7582
Max Act: 9.6957. Min Act: -0.1700
Data Index: 272251 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19