Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.7212. Min Act: -0.1700
Data Index: 7700861 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.6275. Min Act: -0.1700
Data Index: 5960909 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.6275. Min Act: -0.1700
Data Index: 5124738 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.6275. Min Act: -0.1700
Data Index: 4078542 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.6275. Min Act: -0.1700
Data Index: 1120340 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5650. Min Act: -0.1700
Data Index: 4674064 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5650. Min Act: -0.1700
Data Index: 267993 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5337. Min Act: -0.1700
Data Index: 3538855 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5650. Min Act: -0.1700
Data Index: 2269001 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5650. Min Act: -0.1700
Data Index: 3305081 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5337. Min Act: -0.1700
Data Index: 4891490 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5025. Min Act: -0.1700
Data Index: 6703469 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5025. Min Act: -0.1700
Data Index: 2082701 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.5025. Min Act: -0.1700
Data Index: 937933 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.4712. Min Act: -0.1700
Data Index: 7093530 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.4712. Min Act: -0.1700
Data Index: 3000966 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.4087. Min Act: -0.1700
Data Index: 8810537 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.3775. Min Act: -0.1700
Data Index: 6913750 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.4087. Min Act: -0.1700
Data Index: 6867181 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7212. Min Range: -4.7212
Max Act: 4.4087. Min Act: -0.1700
Data Index: 5410065 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19