Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.7177. Min Act: -0.1700
Data Index: 4059640 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6864. Min Act: -0.1700
Data Index: 6568485 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6551. Min Act: -0.1700
Data Index: 1708209 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6551. Min Act: -0.1700
Data Index: 642101 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6238. Min Act: -0.1700
Data Index: 2545198 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6082. Min Act: -0.1700
Data Index: 6990357 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6082. Min Act: -0.1700
Data Index: 7073432 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.6082. Min Act: -0.1700
Data Index: 7171444 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5925. Min Act: -0.1700
Data Index: 958371 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5925. Min Act: -0.1700
Data Index: 5520122 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5925. Min Act: -0.1700
Data Index: 6849385 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5768. Min Act: -0.1700
Data Index: 1668526 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5768. Min Act: -0.1700
Data Index: 6638186 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5612. Min Act: -0.1700
Data Index: 3022657 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5768. Min Act: -0.1700
Data Index: 7873889 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5612. Min Act: -0.1700
Data Index: 135797 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5455. Min Act: -0.1700
Data Index: 4648757 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5299. Min Act: -0.1700
Data Index: 6140448 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5455. Min Act: -0.1700
Data Index: 3770201 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7177. Min Range: -3.7177
Max Act: 3.5455. Min Act: -0.1700
Data Index: 8079971 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19