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

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

Neuron 2572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2122. Min Range: -1.2122

Max Act: 1.2122. Min Act: -0.0000

Data Index: 156414 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.9665. Min Act: -0.0000

Data Index: 537140 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 1.2122. Min Range: -1.2122

Max Act: 1.0120. Min Act: 0.0001

Data Index: 261322 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.9795. Min Act: -0.0000

Data Index: 46985 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.9034. Min Act: -0.0000

Data Index: 143633 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8683. Min Act: -0.0000

Data Index: 991510 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8552. Min Act: -0.0000

Data Index: 35383 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8278. Min Act: 0.0000

Data Index: 3201 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8781. Min Act: 0.0001

Data Index: 451032 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7958. Min Act: 0.0001

Data Index: 347609 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8593. Min Act: -0.0000

Data Index: 558470 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1063360 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8282. Min Act: -0.0000

Data Index: 524598 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7953. Min Act: 0.0001

Data Index: 868707 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7792. Min Act: 0.0000

Data Index: 94405 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1033043 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.8023. Min Act: -0.0000

Data Index: 295076 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7964. Min Act: 0.0001

Data Index: 1333242 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7314. Min Act: -0.0000

Data Index: 65265 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.2122. Min Range: -1.2122

Max Act: 0.7354. Min Act: 0.0001

Data Index: 225367 (C4 (Web Text))

Max Activating Token Index: 1002