Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5323. Min Range: -7.5323
Max Act: 7.5323. Min Act: -0.1700
Data Index: 8228894 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5323. Min Range: -7.5323
Max Act: 7.0635. Min Act: -0.1700
Data Index: 506328 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5323. Min Range: -7.5323
Max Act: 7.0323. Min Act: -0.1700
Data Index: 2537621 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3959825 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.9385. Min Act: -0.1700
Data Index: 2490636 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.9698. Min Act: -0.1700
Data Index: 4536655 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.8448. Min Act: -0.1700
Data Index: 5857260 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 8315614 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 5899884 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 7209322 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 2488487 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 3005071 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7198. Min Act: -0.1700
Data Index: 2114464 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7510. Min Act: -0.1700
Data Index: 5322310 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7510. Min Act: -0.1700
Data Index: 8392105 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.7198. Min Act: -0.1700
Data Index: 4329626 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.6573. Min Act: -0.1700
Data Index: 370850 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3331852 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.6885. Min Act: -0.1700
Data Index: 4648923 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5323. Min Range: -7.5323
Max Act: 6.6573. Min Act: -0.1700
Data Index: 7469628 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19