Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.9614. Min Act: -0.1700
Data Index: 8489225 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.8989. Min Act: -0.1700
Data Index: 4476163 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.8364. Min Act: -0.1700
Data Index: 1109121 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.7426. Min Act: -0.1700
Data Index: 274828 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6801. Min Act: -0.1700
Data Index: 1139648 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.7114. Min Act: -0.1700
Data Index: 3619747 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4094190 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1661961 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1571419 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6489. Min Act: -0.1700
Data Index: 8576209 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6489. Min Act: -0.1700
Data Index: 3813562 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6176. Min Act: -0.1700
Data Index: 6056345 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.6176. Min Act: -0.1700
Data Index: 7403709 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1495105 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1447712 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.4926. Min Act: -0.1700
Data Index: 5874971 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.5239. Min Act: -0.1700
Data Index: 5591469 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.5239. Min Act: -0.1700
Data Index: 1571420 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.5239. Min Act: -0.1700
Data Index: 1614393 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9614. Min Range: -5.9614
Max Act: 5.4926. Min Act: -0.1700
Data Index: 5594383 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19