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

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

Neuron 626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1296544 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.6311. Min Act: -0.0000

Data Index: 1067825 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.7227. Min Act: -0.0000

Data Index: 318549 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5502. Min Act: -0.0000

Data Index: 607010 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5506. Min Act: -0.0000

Data Index: 839150 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5737. Min Act: -0.0000

Data Index: 1051200 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4818. Min Act: -0.0000

Data Index: 304104 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5114. Min Act: -0.0000

Data Index: 18695 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5041. Min Act: -0.0000

Data Index: 295157 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5076. Min Act: -0.0000

Data Index: 1256652 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4531. Min Act: -0.0000

Data Index: 110100 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4853. Min Act: -0.0000

Data Index: 654639 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4848. Min Act: -0.0000

Data Index: 120143 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4422. Min Act: -0.0000

Data Index: 482548 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4230. Min Act: -0.0000

Data Index: 661205 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1292541 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4502. Min Act: -0.0000

Data Index: 638357 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.4665. Min Act: -0.0000

Data Index: 239481 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.3582. Min Act: -0.0000

Data Index: 34826 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 1.7227. Min Range: -1.7227

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1131348 (C4 (Web Text))

Max Activating Token Index: 100