Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0305. Min Range: -8.0305
Max Act: 8.0305. Min Act: -0.1700
Data Index: 1388482 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.8117. Min Act: -0.1700
Data Index: 1346075 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.7492. Min Act: -0.1700
Data Index: 2887125 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.6867. Min Act: -0.1700
Data Index: 2245342 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.6555. Min Act: -0.1700
Data Index: 8562543 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.6242. Min Act: -0.1700
Data Index: 7201740 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.5617. Min Act: -0.1700
Data Index: 6925080 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.5617. Min Act: -0.1700
Data Index: 8575125 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.5617. Min Act: -0.1700
Data Index: 7824264 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.5305. Min Act: -0.1700
Data Index: 4337218 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4992. Min Act: -0.1700
Data Index: 5067171 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4680. Min Act: -0.1700
Data Index: 6780462 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4680. Min Act: -0.1700
Data Index: 2036696 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4680. Min Act: -0.1700
Data Index: 4775074 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4367. Min Act: -0.1700
Data Index: 8466709 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4367. Min Act: -0.1700
Data Index: 2401672 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4367. Min Act: -0.1700
Data Index: 4148469 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.3742. Min Act: -0.1700
Data Index: 7714323 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.4055. Min Act: -0.1700
Data Index: 2527585 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0305. Min Range: -8.0305
Max Act: 7.3430. Min Act: -0.1700
Data Index: 6291327 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19