Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3331 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.3565. Min Act: -0.1700
Data Index: 1601068 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.2315. Min Act: -0.1700
Data Index: 5782054 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3565. Min Range: -7.3565
Max Act: 7.1378. Min Act: -0.1700
Data Index: 5852551 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9815. Min Act: -0.1700
Data Index: 7663652 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9190. Min Act: -0.1700
Data Index: 3225745 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.9503. Min Act: -0.1700
Data Index: 6160712 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.8253. Min Act: -0.1700
Data Index: 409394 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.8253. Min Act: -0.1700
Data Index: 3815858 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.8253. Min Act: -0.1700
Data Index: 6537830 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.7940. Min Act: -0.1700
Data Index: 3830753 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.7628. Min Act: -0.1700
Data Index: 8693058 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.7315. Min Act: -0.1700
Data Index: 2256305 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.6378. Min Act: -0.1700
Data Index: 3727206 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7663650 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.6065. Min Act: -0.1700
Data Index: 959756 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 3795280 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 6231156 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 1479266 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 4209663 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3565. Min Range: -7.3565
Max Act: 6.5440. Min Act: -0.1700
Data Index: 6107309 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19