Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.6176. Min Act: -0.1700
Data Index: 5028056 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.5864. Min Act: -0.1700
Data Index: 7093371 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.5239. Min Act: -0.1700
Data Index: 603201 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.5239. Min Act: -0.1700
Data Index: 2172845 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4926. Min Act: -0.1700
Data Index: 108346 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4926. Min Act: -0.1700
Data Index: 4658475 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4614. Min Act: -0.1700
Data Index: 4883470 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4301. Min Act: -0.1700
Data Index: 5754810 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3989. Min Act: -0.1700
Data Index: 1441065 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4301. Min Act: -0.1700
Data Index: 7351452 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.4301. Min Act: -0.1700
Data Index: 5353587 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3989. Min Act: -0.1700
Data Index: 3594064 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3676. Min Act: -0.1700
Data Index: 5229433 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3676. Min Act: -0.1700
Data Index: 3428464 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3364. Min Act: -0.1700
Data Index: 4302177 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3364. Min Act: -0.1700
Data Index: 2849618 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3989. Min Act: -0.1700
Data Index: 6320110 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3051. Min Act: -0.1700
Data Index: 5295606 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3364. Min Act: -0.1700
Data Index: 254594 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6176. Min Range: -4.6176
Max Act: 4.3364. Min Act: -0.1700
Data Index: 5764762 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19