Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 196 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.3536. Min Act: -0.0000

Data Index: 473146 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.2066. Min Act: -0.0000

Data Index: 273182 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1017868 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.1188. Min Act: -0.0000

Data Index: 719084 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.9162. Min Act: -0.0000

Data Index: 952640 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.8968. Min Act: -0.0000

Data Index: 1269288 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.9988. Min Act: -0.0000

Data Index: 385211 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1122355 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.4991. Min Act: -0.0000

Data Index: 406017 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.6860. Min Act: -0.0000

Data Index: 970876 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.5106. Min Act: -0.0000

Data Index: 939241 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.4882. Min Act: -0.0000

Data Index: 830397 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.5788. Min Act: -0.0000

Data Index: 532977 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.4778. Min Act: -0.0000

Data Index: 875271 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1231324 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.5408. Min Act: -0.0000

Data Index: 730192 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.4216. Min Act: -0.0000

Data Index: 354509 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.3384. Min Act: -0.0000

Data Index: 280980 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1323173 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.1348. Min Act: -0.0000

Data Index: 158457 (C4 (Web Text))

Max Activating Token Index: 975