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

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

Neuron 5149 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.7711. Min Act: -0.0000

Data Index: 1409148 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1211820 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1184873 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.6037. Min Act: -0.0000

Data Index: 1339603 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5770. Min Act: -0.0000

Data Index: 651436 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.6459. Min Act: -0.0000

Data Index: 657109 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5248. Min Act: -0.0000

Data Index: 463774 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4476. Min Act: -0.0000

Data Index: 219721 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1209438 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5108. Min Act: -0.0000

Data Index: 490145 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4292. Min Act: -0.0000

Data Index: 981541 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1267296 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4354. Min Act: -0.0000

Data Index: 134148 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4377. Min Act: -0.0000

Data Index: 811244 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4354. Min Act: -0.0000

Data Index: 587502 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4228. Min Act: -0.0000

Data Index: 873927 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1189770 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1200498 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1026230 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.7711. Min Range: -1.7711

Max Act: 1.4372. Min Act: -0.0000

Data Index: 181395 (C4 (Web Text))

Max Activating Token Index: 240