Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.7769. Min Act: -0.1700
Data Index: 6786616 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.7456. Min Act: -0.1700
Data Index: 8242009 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.6206. Min Act: -0.1700
Data Index: 7754724 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5894. Min Act: -0.1700
Data Index: 2564923 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.6519. Min Act: -0.1700
Data Index: 2666254 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5581. Min Act: -0.1700
Data Index: 863374 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5581. Min Act: -0.1700
Data Index: 1404016 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5269. Min Act: -0.1700
Data Index: 3518073 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5269. Min Act: -0.1700
Data Index: 24216 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4956. Min Act: -0.1700
Data Index: 8073190 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.5269. Min Act: -0.1700
Data Index: 573713 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4956. Min Act: -0.1700
Data Index: 8085214 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4019. Min Act: -0.1700
Data Index: 4308809 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4331. Min Act: -0.1700
Data Index: 1613602 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4019. Min Act: -0.1700
Data Index: 350010 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4331. Min Act: -0.1700
Data Index: 4967056 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4019. Min Act: -0.1700
Data Index: 2289478 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4331. Min Act: -0.1700
Data Index: 7095332 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.4019. Min Act: -0.1700
Data Index: 7474390 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7769. Min Range: -5.7769
Max Act: 5.3394. Min Act: -0.1700
Data Index: 1646120 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19