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

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

Neuron 1659 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.9250. Min Act: -0.0000

Data Index: 900162 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.7111. Min Act: -0.0000

Data Index: 230624 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.5070. Min Act: -0.0000

Data Index: 448181 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.2084. Min Act: -0.0000

Data Index: 304235 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.2281. Min Act: -0.0000

Data Index: 1131369 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 6.9250. Min Range: -6.9250

Max Act: 6.0179. Min Act: -0.0000

Data Index: 261535 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.6711. Min Act: -0.0000

Data Index: 262357 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.9245. Min Act: -0.0000

Data Index: 144354 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.5512. Min Act: -0.0000

Data Index: 1080447 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.5940. Min Act: -0.0000

Data Index: 600693 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.0541. Min Act: -0.0000

Data Index: 656652 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.2516. Min Act: -0.0000

Data Index: 944467 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 6.9250. Min Range: -6.9250

Max Act: 5.0631. Min Act: -0.0000

Data Index: 366130 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 6.9250. Min Range: -6.9250

Max Act: 4.9648. Min Act: -0.0000

Data Index: 374412 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 6.9250. Min Range: -6.9250

Max Act: 4.4693. Min Act: -0.0000

Data Index: 1300946 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 6.9250. Min Range: -6.9250

Max Act: 4.5158. Min Act: -0.0000

Data Index: 872242 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 6.9250. Min Range: -6.9250

Max Act: 4.2190. Min Act: -0.0000

Data Index: 763473 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 6.9250. Min Range: -6.9250

Max Act: 4.2293. Min Act: -0.0000

Data Index: 1306608 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 6.9250. Min Range: -6.9250

Max Act: 3.8550. Min Act: -0.0000

Data Index: 169992 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 6.9250. Min Range: -6.9250

Max Act: 3.7841. Min Act: -0.0000

Data Index: 33425 (C4 (Web Text))

Max Activating Token Index: 635