Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.9270. Min Act: -0.1700
Data Index: 6460647 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.9270. Min Act: -0.1700
Data Index: 202447 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.9355. Min Act: -0.1700
Data Index: 8212111 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8929. Min Act: -0.1700
Data Index: 6587142 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8844. Min Act: -0.1700
Data Index: 868662 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8502. Min Act: -0.1700
Data Index: 8456793 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8502. Min Act: -0.1700
Data Index: 1579172 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8588. Min Act: -0.1700
Data Index: 2031353 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8416. Min Act: -0.1700
Data Index: 2498094 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8331. Min Act: -0.1700
Data Index: 496385 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8331. Min Act: -0.1700
Data Index: 1674680 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8245. Min Act: -0.1700
Data Index: 4926024 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8245. Min Act: -0.1700
Data Index: 868660 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8159. Min Act: -0.1700
Data Index: 2808561 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8331. Min Act: -0.1700
Data Index: 6956921 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8159. Min Act: -0.1700
Data Index: 6126523 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.7987. Min Act: -0.1700
Data Index: 2969794 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8073. Min Act: -0.1700
Data Index: 3869189 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.7815. Min Act: -0.1700
Data Index: 53457 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9355. Min Range: -1.9355
Max Act: 1.8073. Min Act: -0.1700
Data Index: 4226481 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19