Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.6047. Min Act: -0.1700
Data Index: 1507503 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.5422. Min Act: -0.1700
Data Index: 6031744 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.4797. Min Act: -0.1700
Data Index: 5572227 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.4172. Min Act: -0.1700
Data Index: 967382 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.3547. Min Act: -0.1700
Data Index: 4572646 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2922. Min Act: -0.1700
Data Index: 5954646 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2922. Min Act: -0.1700
Data Index: 1216037 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2922. Min Act: -0.1700
Data Index: 1701182 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2922. Min Act: -0.1700
Data Index: 1961382 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2609. Min Act: -0.1700
Data Index: 1780160 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2609. Min Act: -0.1700
Data Index: 4589466 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 100362 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2609. Min Act: -0.1700
Data Index: 6199814 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 4496141 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 810652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 7647789 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 5007832 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 633026 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.2297. Min Act: -0.1700
Data Index: 191698 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6047. Min Range: -4.6047
Max Act: 4.1984. Min Act: -0.1700
Data Index: 6284870 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19