Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5698 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.9962. Min Act: -0.1700
Data Index: 1055304 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.8712. Min Act: -0.1700
Data Index: 1344371 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7774. Min Act: -0.1700
Data Index: 2740809 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7462. Min Act: -0.1700
Data Index: 314200 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7774. Min Act: -0.1700
Data Index: 8423963 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7462. Min Act: -0.1700
Data Index: 4957362 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7462. Min Act: -0.1700
Data Index: 6254091 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6837. Min Act: -0.1700
Data Index: 872103 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7149. Min Act: -0.1700
Data Index: 6409897 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7149. Min Act: -0.1700
Data Index: 8275218 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7149. Min Act: -0.1700
Data Index: 6409905 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2819059 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6837. Min Act: -0.1700
Data Index: 2853726 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6837. Min Act: -0.1700
Data Index: 7479702 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6212. Min Act: -0.1700
Data Index: 4262812 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6212. Min Act: -0.1700
Data Index: 5535191 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6524. Min Act: -0.1700
Data Index: 1229982 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6212. Min Act: -0.1700
Data Index: 4619070 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6524. Min Act: -0.1700
Data Index: 7479706 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9962. Min Range: -4.9962
Max Act: 4.6212. Min Act: -0.1700
Data Index: 2720579 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19