Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.1419. Min Act: -0.1700
Data Index: 424237 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.1419. Min Act: -0.1700
Data Index: 424229 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.1107. Min Act: -0.1700
Data Index: 2830335 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 6408379 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 2395695 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0482. Min Act: -0.1700
Data Index: 4646184 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 7404124 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 158816 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0794. Min Act: -0.1700
Data Index: 1298335 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0169. Min Act: -0.1700
Data Index: 4817769 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2668281 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0169. Min Act: -0.1700
Data Index: 1298334 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7480484 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0169. Min Act: -0.1700
Data Index: 505666 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1419. Min Range: -7.1419
Max Act: 7.0482. Min Act: -0.1700
Data Index: 7676112 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1419. Min Range: -7.1419
Max Act: 6.9857. Min Act: -0.1700
Data Index: 2668283 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1419. Min Range: -7.1419
Max Act: 6.9544. Min Act: -0.1700
Data Index: 8815388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1419. Min Range: -7.1419
Max Act: 6.9544. Min Act: -0.1700
Data Index: 4675615 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1419. Min Range: -7.1419
Max Act: 6.9544. Min Act: -0.1700
Data Index: 2355112 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1419. Min Range: -7.1419
Max Act: 6.9232. Min Act: -0.1700
Data Index: 5557226 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19