Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 306 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.1559. Min Act: -0.1700
Data Index: 5802567 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.1247. Min Act: -0.1700
Data Index: 2014718 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.0934. Min Act: -0.1700
Data Index: 6796108 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.0622. Min Act: -0.1700
Data Index: 1565839 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.0309. Min Act: -0.1700
Data Index: 1120601 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1559. Min Range: -5.1559
Max Act: 5.0309. Min Act: -0.1700
Data Index: 3628394 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.9997. Min Act: -0.1700
Data Index: 4584041 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5710397 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.9684. Min Act: -0.1700
Data Index: 4473095 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.9372. Min Act: -0.1700
Data Index: 5237223 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.9059. Min Act: -0.1700
Data Index: 5255230 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8747. Min Act: -0.1700
Data Index: 4181702 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8747. Min Act: -0.1700
Data Index: 546503 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8747. Min Act: -0.1700
Data Index: 2014512 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8434. Min Act: -0.1700
Data Index: 4257619 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8434. Min Act: -0.1700
Data Index: 5357815 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8122. Min Act: -0.1700
Data Index: 5314721 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8122. Min Act: -0.1700
Data Index: 446288 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8122. Min Act: -0.1700
Data Index: 140421 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1559. Min Range: -5.1559
Max Act: 4.8122. Min Act: -0.1700
Data Index: 1555688 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19