Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4045 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.8272. Min Act: -0.1700
Data Index: 1167851 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.8272. Min Act: -0.1700
Data Index: 973709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.7647. Min Act: -0.1700
Data Index: 3280013 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.7647. Min Act: -0.1700
Data Index: 6155673 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.7022. Min Act: -0.1700
Data Index: 8085182 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.7022. Min Act: -0.1700
Data Index: 8291774 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.7022. Min Act: -0.1700
Data Index: 2066029 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.6397. Min Act: -0.1700
Data Index: 4356311 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.6397. Min Act: -0.1700
Data Index: 3586908 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5147. Min Act: -0.1700
Data Index: 2935708 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.6397. Min Act: -0.1700
Data Index: 6520301 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5772. Min Act: -0.1700
Data Index: 1800903 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5772. Min Act: -0.1700
Data Index: 7770716 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5772. Min Act: -0.1700
Data Index: 8103704 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5147. Min Act: -0.1700
Data Index: 6242220 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5147. Min Act: -0.1700
Data Index: 2263074 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.4522. Min Act: -0.1700
Data Index: 4529348 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5147. Min Act: -0.1700
Data Index: 7343975 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.5147. Min Act: -0.1700
Data Index: 95273 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8272. Min Range: -8.8272
Max Act: 8.4522. Min Act: -0.1700
Data Index: 5379227 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19