Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.4448. Min Act: -0.1700
Data Index: 3068604 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.4135. Min Act: -0.1700
Data Index: 3613813 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.2573. Min Act: -0.1700
Data Index: 8153461 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.2260. Min Act: -0.1700
Data Index: 513209 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1948. Min Act: -0.1700
Data Index: 4323746 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1948. Min Act: -0.1700
Data Index: 1256106 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1323. Min Act: -0.1700
Data Index: 6815222 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1323. Min Act: -0.1700
Data Index: 1185816 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1323. Min Act: -0.1700
Data Index: 7300681 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1010. Min Act: -0.1700
Data Index: 2106690 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.1010. Min Act: -0.1700
Data Index: 7694748 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0698. Min Act: -0.1700
Data Index: 3873471 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0698. Min Act: -0.1700
Data Index: 2097441 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0385. Min Act: -0.1700
Data Index: 3976228 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0385. Min Act: -0.1700
Data Index: 3114651 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0698. Min Act: -0.1700
Data Index: 6962643 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0385. Min Act: -0.1700
Data Index: 2290511 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4448. Min Range: -7.4448
Max Act: 7.0073. Min Act: -0.1700
Data Index: 1183790 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4448. Min Range: -7.4448
Max Act: 6.9760. Min Act: -0.1700
Data Index: 2163050 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4448. Min Range: -7.4448
Max Act: 6.9135. Min Act: -0.1700
Data Index: 6396692 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19