Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.6983. Min Act: -0.0000

Data Index: 530504 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.7938. Min Act: -0.0000

Data Index: 1136735 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.5495. Min Act: -0.0000

Data Index: 396253 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.5243. Min Act: -0.0000

Data Index: 997800 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.5066. Min Act: -0.0000

Data Index: 940788 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.4846. Min Act: -0.0000

Data Index: 405844 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.4828. Min Act: -0.0000

Data Index: 252788 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.4326. Min Act: -0.0000

Data Index: 662911 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1226402 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.4372. Min Act: -0.0000

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.4221. Min Act: -0.0000

Data Index: 462858 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.2908. Min Act: -0.0000

Data Index: 170836 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1155835 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.3542. Min Act: -0.0000

Data Index: 69680 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.2495. Min Act: -0.0000

Data Index: 229450 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.3036. Min Act: -0.0000

Data Index: 102766 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.2974. Min Act: -0.0000

Data Index: 945865 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.2820. Min Act: -0.0000

Data Index: 704861 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.1531. Min Act: -0.0000

Data Index: 635228 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.7938. Min Range: -1.7938

Max Act: 1.1341. Min Act: -0.0000

Data Index: 1206930 (C4 (Web Text))

Max Activating Token Index: 142