Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2302. Min Range: -6.2302
Max Act: 6.2302. Min Act: -0.1700
Data Index: 1047489 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.8865. Min Act: -0.1700
Data Index: 427357 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.8240. Min Act: -0.1700
Data Index: 181719 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.7302. Min Act: -0.1700
Data Index: 7026054 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 8167960 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 7489605 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6386721 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 6995227 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5740. Min Act: -0.1700
Data Index: 8562931 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1550987 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5740. Min Act: -0.1700
Data Index: 8810437 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5740. Min Act: -0.1700
Data Index: 4114024 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5427. Min Act: -0.1700
Data Index: 7614156 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.5115. Min Act: -0.1700
Data Index: 7795381 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4802. Min Act: -0.1700
Data Index: 5875613 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4802. Min Act: -0.1700
Data Index: 8327005 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4802. Min Act: -0.1700
Data Index: 2613595 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4802. Min Act: -0.1700
Data Index: 7474236 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4177. Min Act: -0.1700
Data Index: 6616593 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2302. Min Range: -6.2302
Max Act: 5.4490. Min Act: -0.1700
Data Index: 2465418 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19