Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1242523 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.8633. Min Act: -0.1700
Data Index: 2431080 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.8476. Min Act: -0.1700
Data Index: 897305 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.8007. Min Act: -0.1700
Data Index: 5470076 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.7694. Min Act: -0.1700
Data Index: 5470077 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.7069. Min Act: -0.1700
Data Index: 6299620 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.6912. Min Act: -0.1700
Data Index: 1345232 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.6286. Min Act: -0.1700
Data Index: 1141675 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.6286. Min Act: -0.1700
Data Index: 8199142 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.6443. Min Act: -0.1700
Data Index: 1925937 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.6130. Min Act: -0.1700
Data Index: 2603324 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5817. Min Act: -0.1700
Data Index: 7742557 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5660. Min Act: -0.1700
Data Index: 5120299 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5817. Min Act: -0.1700
Data Index: 7925614 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5660. Min Act: -0.1700
Data Index: 1120584 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5817. Min Act: -0.1700
Data Index: 1495012 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5660. Min Act: -0.1700
Data Index: 754455 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5504. Min Act: -0.1700
Data Index: 7068179 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5504. Min Act: -0.1700
Data Index: 8624654 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8789. Min Range: -3.8789
Max Act: 3.5347. Min Act: -0.1700
Data Index: 6931108 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19