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

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

Neuron 660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1025981 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1212047 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0172. Min Act: -0.0006

Data Index: 248494 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0159. Min Act: -0.0006

Data Index: 336192 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0160. Min Act: -0.0006

Data Index: 463521 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0156. Min Act: -0.0006

Data Index: 352736 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0154. Min Act: -0.0006

Data Index: 655608 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0164. Min Act: -0.0006

Data Index: 414433 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0149. Min Act: -0.0006

Data Index: 944104 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 539242 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0006

Data Index: 510801 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0136. Min Act: -0.0006

Data Index: 444155 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0156. Min Act: -0.0006

Data Index: 354883 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1266238 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0140. Min Act: -0.0006

Data Index: 260790 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0150. Min Act: -0.0006

Data Index: 861294 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0140. Min Act: -0.0006

Data Index: 722293 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1115090 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0138. Min Act: -0.0006

Data Index: 663607 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0141. Min Act: -0.0006

Data Index: 965852 (C4 (Web Text))

Max Activating Token Index: 507