Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.4315. Min Act: -0.1700
Data Index: 1250270 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.4003. Min Act: -0.1700
Data Index: 3971538 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.3690. Min Act: -0.1700
Data Index: 5625712 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.3378. Min Act: -0.1700
Data Index: 4371309 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.3065. Min Act: -0.1700
Data Index: 6580979 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.3065. Min Act: -0.1700
Data Index: 5179073 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.2753. Min Act: -0.1700
Data Index: 754247 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.2128. Min Act: -0.1700
Data Index: 5977868 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.1815. Min Act: -0.1700
Data Index: 1332784 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.1190. Min Act: -0.1700
Data Index: 7792333 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0878. Min Act: -0.1700
Data Index: 6826134 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0878. Min Act: -0.1700
Data Index: 755802 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0253. Min Act: -0.1700
Data Index: 2381652 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0565. Min Act: -0.1700
Data Index: 2513401 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0565. Min Act: -0.1700
Data Index: 278795 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0253. Min Act: -0.1700
Data Index: 6641418 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0565. Min Act: -0.1700
Data Index: 2228818 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0565. Min Act: -0.1700
Data Index: 446768 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0253. Min Act: -0.1700
Data Index: 4293 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4315. Min Range: -6.4315
Max Act: 6.0253. Min Act: -0.1700
Data Index: 249189 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19