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

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

Neuron 1015 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4771. Min Range: -5.4771

Max Act: 5.4771. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 5.4771. Min Range: -5.4771

Max Act: 5.2538. Min Act: -0.0000

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 5.4771. Min Range: -5.4771

Max Act: 4.0248. Min Act: -0.0000

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 5.4771. Min Range: -5.4771

Max Act: 4.0241. Min Act: -0.0000

Data Index: 1060319 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.0443. Min Act: -0.0000

Data Index: 1315282 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.3774. Min Act: -0.0001

Data Index: 1116593 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.6256. Min Act: -0.0001

Data Index: 1626906 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.4428. Min Act: -0.0000

Data Index: 622924 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 5.4771. Min Range: -5.4771

Max Act: 4.0498. Min Act: -0.0000

Data Index: 208038 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.0918. Min Act: -0.0000

Data Index: 763298 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.1732. Min Act: -0.0000

Data Index: 894566 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.0472. Min Act: -0.0000

Data Index: 1157764 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.2891. Min Act: -0.0001

Data Index: 1129081 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.2044. Min Act: -0.0000

Data Index: 296474 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 5.4771. Min Range: -5.4771

Max Act: 2.8371. Min Act: -0.0000

Data Index: 598211 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 5.4771. Min Range: -5.4771

Max Act: 2.8188. Min Act: -0.0000

Data Index: 171974 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.5087. Min Act: -0.0000

Data Index: 181613 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.8319. Min Act: -0.0000

Data Index: 1271782 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.1851. Min Act: -0.0000

Data Index: 551300 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 5.4771. Min Range: -5.4771

Max Act: 3.3168. Min Act: -0.0000

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 271