Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.2815. Min Act: -0.1700
Data Index: 8680910 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.1252. Min Act: -0.1700
Data Index: 1555907 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.0627. Min Act: -0.1700
Data Index: 5826298 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.0627. Min Act: -0.1700
Data Index: 7121429 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.0315. Min Act: -0.1700
Data Index: 5064953 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2815. Min Range: -6.2815
Max Act: 6.0315. Min Act: -0.1700
Data Index: 8294921 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6566722 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9377. Min Act: -0.1700
Data Index: 7083593 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9377. Min Act: -0.1700
Data Index: 5826295 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9377. Min Act: -0.1700
Data Index: 7121426 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9377. Min Act: -0.1700
Data Index: 4222605 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9377. Min Act: -0.1700
Data Index: 7451783 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5437013 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9065. Min Act: -0.1700
Data Index: 21071 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.9065. Min Act: -0.1700
Data Index: 150877 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.8440. Min Act: -0.1700
Data Index: 3053860 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.8440. Min Act: -0.1700
Data Index: 5531263 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.8440. Min Act: -0.1700
Data Index: 7142224 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.8440. Min Act: -0.1700
Data Index: 6591721 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2815. Min Range: -6.2815
Max Act: 5.8127. Min Act: -0.1700
Data Index: 1483584 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19