Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.4508. Min Act: -0.1700
Data Index: 5379472 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.3571. Min Act: -0.1700
Data Index: 1191733 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.3883. Min Act: -0.1700
Data Index: 1252910 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.2946. Min Act: -0.1700
Data Index: 7668822 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.2633. Min Act: -0.1700
Data Index: 8574747 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.2008. Min Act: -0.1700
Data Index: 6153000 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.2321. Min Act: -0.1700
Data Index: 7402510 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1696. Min Act: -0.1700
Data Index: 7041157 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1071. Min Act: -0.1700
Data Index: 2158287 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1696. Min Act: -0.1700
Data Index: 7336391 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1383. Min Act: -0.1700
Data Index: 3355645 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1383. Min Act: -0.1700
Data Index: 4696746 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.1071. Min Act: -0.1700
Data Index: 8676744 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0758. Min Act: -0.1700
Data Index: 2580207 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0758. Min Act: -0.1700
Data Index: 563072 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0445. Min Act: -0.1700
Data Index: 1099178 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0445. Min Act: -0.1700
Data Index: 302723 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0445. Min Act: -0.1700
Data Index: 5227575 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0133. Min Act: -0.1700
Data Index: 4170096 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4508. Min Range: -4.4508
Max Act: 4.0133. Min Act: -0.1700
Data Index: 6155514 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19