Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 380 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1177095 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0194. Min Act: -0.0006

Data Index: 46160 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0180. Min Act: -0.0006

Data Index: 273106 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0178. Min Act: -0.0006

Data Index: 738584 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0180. Min Act: -0.0006

Data Index: 474299 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0006

Data Index: 590755 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0176. Min Act: -0.0006

Data Index: 831475 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1092336 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0005

Data Index: 1460674 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1139602 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1449778 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0169. Min Act: -0.0006

Data Index: 854974 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0177. Min Act: -0.0006

Data Index: 87705 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1248652 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0171. Min Act: -0.0006

Data Index: 633666 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0167. Min Act: -0.0006

Data Index: 483527 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0170. Min Act: -0.0006

Data Index: 844644 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0006

Data Index: 832561 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1608773 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1487448 (Python Code)

Max Activating Token Index: 137