Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 533 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2789. Min Range: -8.2789
Max Act: 8.2789. Min Act: -0.1700
Data Index: 6164588 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2789. Min Range: -8.2789
Max Act: 7.1851. Min Act: -0.1700
Data Index: 7490381 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2789. Min Range: -8.2789
Max Act: 7.1226. Min Act: -0.1700
Data Index: 5443231 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2789. Min Range: -8.2789
Max Act: 7.0914. Min Act: -0.1700
Data Index: 552276 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.9351. Min Act: -0.1700
Data Index: 6094293 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.9351. Min Act: -0.1700
Data Index: 6930382 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.9039. Min Act: -0.1700
Data Index: 4490885 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.8414. Min Act: -0.1700
Data Index: 6242781 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.8101. Min Act: -0.1700
Data Index: 4125360 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7789. Min Act: -0.1700
Data Index: 6541992 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7789. Min Act: -0.1700
Data Index: 1790615 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7476. Min Act: -0.1700
Data Index: 6769508 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7476. Min Act: -0.1700
Data Index: 4809394 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7476. Min Act: -0.1700
Data Index: 1256197 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.7164. Min Act: -0.1700
Data Index: 1268585 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.6851. Min Act: -0.1700
Data Index: 1308871 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.6851. Min Act: -0.1700
Data Index: 6401046 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7597680 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.6226. Min Act: -0.1700
Data Index: 2794600 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2789. Min Range: -8.2789
Max Act: 6.6539. Min Act: -0.1700
Data Index: 7864568 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19