Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.8225. Min Act: -0.1700
Data Index: 4536087 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.5725. Min Act: -0.1700
Data Index: 8811425 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.5100. Min Act: -0.1700
Data Index: 8811421 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.4788. Min Act: -0.1700
Data Index: 8811430 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.4788. Min Act: -0.1700
Data Index: 6104589 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.3850. Min Act: -0.1700
Data Index: 8811424 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.3225. Min Act: -0.1700
Data Index: 3217005 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.3225. Min Act: -0.1700
Data Index: 3796556 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2600. Min Act: -0.1700
Data Index: 5301158 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2600. Min Act: -0.1700
Data Index: 5785454 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2600. Min Act: -0.1700
Data Index: 5873384 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2288. Min Act: -0.1700
Data Index: 7352424 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2288. Min Act: -0.1700
Data Index: 3085424 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2288. Min Act: -0.1700
Data Index: 3844974 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.2288. Min Act: -0.1700
Data Index: 815084 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.1975. Min Act: -0.1700
Data Index: 527551 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.1975. Min Act: -0.1700
Data Index: 8198149 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.1975. Min Act: -0.1700
Data Index: 1174913 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4297838 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8225. Min Range: -5.8225
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5117478 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19