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

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

Neuron 3729 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1289486 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0213. Min Act: -0.0001

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1328163 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1079069 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1224726 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0162. Min Act: -0.0001

Data Index: 43248 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0160. Min Act: -0.0001

Data Index: 246870 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1145848 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0157. Min Act: -0.0001

Data Index: 285648 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1073395 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0155. Min Act: -0.0001

Data Index: 252856 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1024124 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1242078 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0153. Min Act: -0.0001

Data Index: 389944 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0157. Min Act: -0.0001

Data Index: 635115 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0148. Min Act: -0.0001

Data Index: 715150 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0155. Min Act: -0.0001

Data Index: 1105671 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0157. Min Act: -0.0001

Data Index: 239489 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0152. Min Act: -0.0000

Data Index: 1502857 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0159. Min Act: -0.0001

Data Index: 629056 (C4 (Web Text))

Max Activating Token Index: 200