Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.4364. Min Act: -0.1700
Data Index: 6104236 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7166971 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2669683 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3739. Min Act: -0.1700
Data Index: 5094573 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3114. Min Act: -0.1700
Data Index: 4149600 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3426. Min Act: -0.1700
Data Index: 6480866 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2801. Min Act: -0.1700
Data Index: 773148 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.3114. Min Act: -0.1700
Data Index: 4217762 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7268634 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2801. Min Act: -0.1700
Data Index: 8003217 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2489. Min Act: -0.1700
Data Index: 6583420 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2489. Min Act: -0.1700
Data Index: 465861 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.2176. Min Act: -0.1700
Data Index: 3348234 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1864. Min Act: -0.1700
Data Index: 3048797 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1864. Min Act: -0.1700
Data Index: 6760341 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1551. Min Act: -0.1700
Data Index: 658500 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3927408 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.0926. Min Act: -0.1700
Data Index: 102020 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1239. Min Act: -0.1700
Data Index: 1827366 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4364. Min Range: -5.4364
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3165825 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19