Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2375. Min Range: -3.2375
Max Act: 3.2375. Min Act: -0.1700
Data Index: 5723478 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2375. Min Range: -3.2375
Max Act: 3.0959. Min Act: -0.1700
Data Index: 6073666 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9695. Min Act: -0.1700
Data Index: 4519306 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9695. Min Act: -0.1700
Data Index: 4579276 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9695. Min Act: -0.1700
Data Index: 4997749 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9537. Min Act: -0.1700
Data Index: 3042443 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9537. Min Act: -0.1700
Data Index: 4711659 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9537. Min Act: -0.1700
Data Index: 1728156 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9379. Min Act: -0.1700
Data Index: 8603569 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9379. Min Act: -0.1700
Data Index: 49396 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9220. Min Act: -0.1700
Data Index: 6556609 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9062. Min Act: -0.1700
Data Index: 917661 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9220. Min Act: -0.1700
Data Index: 2987794 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9220. Min Act: -0.1700
Data Index: 3189396 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9062. Min Act: -0.1700
Data Index: 5441698 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.9062. Min Act: -0.1700
Data Index: 1398936 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.8903. Min Act: -0.1700
Data Index: 7801996 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.8903. Min Act: -0.1700
Data Index: 627888 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.8903. Min Act: -0.1700
Data Index: 3241522 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2375. Min Range: -3.2375
Max Act: 2.8745. Min Act: -0.1700
Data Index: 8421064 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19