Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1500351 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0190. Min Act: -0.0001

Data Index: 208026 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0198. Min Act: -0.0001

Data Index: 422689 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1344820 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0191. Min Act: -0.0000

Data Index: 683039 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0001

Data Index: 744014 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0178. Min Act: -0.0001

Data Index: 498679 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0174. Min Act: -0.0001

Data Index: 822851 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0179. Min Act: -0.0000

Data Index: 1377437 (Python Code)

Max Activating Token Index: 415

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0181. Min Act: -0.0001

Data Index: 41247 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0177. Min Act: -0.0000

Data Index: 581503 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0172. Min Act: -0.0001

Data Index: 841724 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0172. Min Act: -0.0000

Data Index: 1396921 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0169. Min Act: -0.0001

Data Index: 491266 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1415836 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1546075 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0001

Data Index: 100666 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0165. Min Act: -0.0000

Data Index: 91882 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0157. Min Act: -0.0001

Data Index: 567700 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1643646 (Python Code)

Max Activating Token Index: 762