Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1900 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0003

Data Index: 992869 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0179. Min Act: -0.0003

Data Index: 540934 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0003

Data Index: 574870 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0003

Data Index: 368288 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0151. Min Act: -0.0003

Data Index: 400926 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0149. Min Act: -0.0003

Data Index: 546543 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0139. Min Act: -0.0003

Data Index: 829847 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0147. Min Act: -0.0003

Data Index: 312025 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0143. Min Act: -0.0003

Data Index: 482927 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0145. Min Act: -0.0002

Data Index: 694155 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0147. Min Act: -0.0002

Data Index: 373836 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0135. Min Act: -0.0003

Data Index: 862511 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0140. Min Act: -0.0003

Data Index: 272188 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0154. Min Act: -0.0003

Data Index: 904613 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1352461 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0140. Min Act: -0.0003

Data Index: 928002 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0137. Min Act: -0.0003

Data Index: 477300 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1381770 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1282400 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0137. Min Act: -0.0003

Data Index: 1406558 (Python Code)

Max Activating Token Index: 880