Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9490. Min Act: -0.1700
Data Index: 6419912 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9490. Min Act: -0.1700
Data Index: 8083377 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9015. Min Act: -0.1700
Data Index: 8814399 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9173. Min Act: -0.1700
Data Index: 4538369 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9332. Min Act: -0.1700
Data Index: 6751491 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9015. Min Act: -0.1700
Data Index: 5675339 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9173. Min Act: -0.1700
Data Index: 3490593 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.9015. Min Act: -0.1700
Data Index: 3282154 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8856. Min Act: -0.1700
Data Index: 6323771 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8856. Min Act: -0.1700
Data Index: 6811556 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8697. Min Act: -0.1700
Data Index: 4062691 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8539. Min Act: -0.1700
Data Index: 5752604 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8856. Min Act: -0.1700
Data Index: 7219535 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8856. Min Act: -0.1700
Data Index: 3271835 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8539. Min Act: -0.1700
Data Index: 212381 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8697. Min Act: -0.1700
Data Index: 8719550 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8380. Min Act: -0.1700
Data Index: 2594370 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8380. Min Act: -0.1700
Data Index: 1453772 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8539. Min Act: -0.1700
Data Index: 8083157 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9490. Min Range: -2.9490
Max Act: 2.8539. Min Act: -0.1700
Data Index: 6309609 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19