Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.9266. Min Act: -0.1700
Data Index: 3679996 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.8641. Min Act: -0.1700
Data Index: 81231 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.8016. Min Act: -0.1700
Data Index: 4536421 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6766. Min Act: -0.1700
Data Index: 2251576 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6766. Min Act: -0.1700
Data Index: 6848565 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6453. Min Act: -0.1700
Data Index: 3685340 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6141. Min Act: -0.1700
Data Index: 1134483 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6141. Min Act: -0.1700
Data Index: 2367379 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.5828. Min Act: -0.1700
Data Index: 2694538 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.6141. Min Act: -0.1700
Data Index: 2411994 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.5828. Min Act: -0.1700
Data Index: 6922745 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.5828. Min Act: -0.1700
Data Index: 7988285 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.5516. Min Act: -0.1700
Data Index: 1735355 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4578. Min Act: -0.1700
Data Index: 1648322 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4578. Min Act: -0.1700
Data Index: 5078411 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4578. Min Act: -0.1700
Data Index: 4628545 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4266. Min Act: -0.1700
Data Index: 7929813 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4266. Min Act: -0.1700
Data Index: 1148704 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.4266. Min Act: -0.1700
Data Index: 7150387 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9266. Min Range: -6.9266
Max Act: 6.3953. Min Act: -0.1700
Data Index: 5571615 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19