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

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

Neuron 3519 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0003

Data Index: 479680 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0184. Min Act: -0.0003

Data Index: 898101 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1317426 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1080029 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0167. Min Act: -0.0003

Data Index: 283961 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0165. Min Act: -0.0003

Data Index: 787077 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1297026 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1174575 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0164. Min Act: -0.0003

Data Index: 382229 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1633545 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0159. Min Act: -0.0003

Data Index: 99057 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0158. Min Act: -0.0003

Data Index: 795228 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0157. Min Act: -0.0003

Data Index: 672722 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1027494 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1599335 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0139. Min Act: -0.0003

Data Index: 474606 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1103451 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0157. Min Act: -0.0003

Data Index: 182929 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1339374 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0153. Min Act: -0.0003

Data Index: 667906 (C4 (Web Text))

Max Activating Token Index: 18