Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.4559. Min Act: -0.1700
Data Index: 7615140 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.3934. Min Act: -0.1700
Data Index: 1382868 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.3621. Min Act: -0.1700
Data Index: 5520471 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.3309. Min Act: -0.1700
Data Index: 8409061 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.2996. Min Act: -0.1700
Data Index: 3935995 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.2684. Min Act: -0.1700
Data Index: 7310392 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.2684. Min Act: -0.1700
Data Index: 3754214 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.1746. Min Act: -0.1700
Data Index: 3449409 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.1121. Min Act: -0.1700
Data Index: 371147 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.1121. Min Act: -0.1700
Data Index: 5340666 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.1121. Min Act: -0.1700
Data Index: 7628184 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 3248224 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0809. Min Act: -0.1700
Data Index: 623068 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2755356 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2597330 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0809. Min Act: -0.1700
Data Index: 5322666 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0809. Min Act: -0.1700
Data Index: 7224318 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 5267744 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 1304440 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4559. Min Range: -5.4559
Max Act: 5.0496. Min Act: -0.1700
Data Index: 2172200 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19