Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4747 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.2774. Min Act: -0.1700
Data Index: 2672669 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.3087. Min Act: -0.1700
Data Index: 5636835 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3454345 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1938857 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.0587. Min Act: -0.1700
Data Index: 7608343 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.0274. Min Act: -0.1700
Data Index: 371939 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7046443 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9962. Min Act: -0.1700
Data Index: 1747331 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3087. Min Range: -5.3087
Max Act: 5.0274. Min Act: -0.1700
Data Index: 8810663 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9649. Min Act: -0.1700
Data Index: 6652370 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9337. Min Act: -0.1700
Data Index: 162140 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9649. Min Act: -0.1700
Data Index: 2560551 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9337. Min Act: -0.1700
Data Index: 2624256 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9024. Min Act: -0.1700
Data Index: 6052522 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9337. Min Act: -0.1700
Data Index: 4341459 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.8712. Min Act: -0.1700
Data Index: 2655224 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9024. Min Act: -0.1700
Data Index: 1858340 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.8712. Min Act: -0.1700
Data Index: 5802086 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9024. Min Act: -0.1700
Data Index: 1206109 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3087. Min Range: -5.3087
Max Act: 4.9024. Min Act: -0.1700
Data Index: 2350223 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19