Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 840 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7850458 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7587. Min Act: -0.1700
Data Index: 8700756 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7587. Min Act: -0.1700
Data Index: 1662420 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7587. Min Act: -0.1700
Data Index: 4645116 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 4558844 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 2958585 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 3365509 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 2779621 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 1303134 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5055771 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 5515288 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 56246 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 6776059 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.7274. Min Act: -0.1700
Data Index: 6003545 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 4770495 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6649. Min Act: -0.1700
Data Index: 3505329 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6649. Min Act: -0.1700
Data Index: 3505328 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 3859478 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5840189 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8212. Min Range: -4.8212
Max Act: 4.6649. Min Act: -0.1700
Data Index: 6068110 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19