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

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

Neuron 3921 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: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0003

Data Index: 343100 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0178. Min Act: -0.0003

Data Index: 2956 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0189. Min Act: -0.0003

Data Index: 832289 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0175. Min Act: -0.0003

Data Index: 678314 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0180. Min Act: -0.0003

Data Index: 102933 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0183. Min Act: -0.0003

Data Index: 785219 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0158. Min Act: -0.0003

Data Index: 756281 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1156045 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0153. Min Act: -0.0003

Data Index: 753733 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0163. Min Act: -0.0003

Data Index: 430688 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1308975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0003

Data Index: 600724 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0169. Min Act: -0.0003

Data Index: 818539 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0148. Min Act: -0.0003

Data Index: 630253 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0176. Min Act: -0.0003

Data Index: 534959 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0128. Min Act: -0.0003

Data Index: 790478 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0150. Min Act: -0.0003

Data Index: 975306 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1163738 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0153. Min Act: -0.0003

Data Index: 101521 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0169. Min Act: -0.0003

Data Index: 630546 (C4 (Web Text))

Max Activating Token Index: 496