Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5976 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0229. Min Act: -0.0001

Data Index: 828456 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1326618 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1310897 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0193. Min Act: -0.0001

Data Index: 939514 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1329888 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1236231 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0173. Min Act: -0.0001

Data Index: 930456 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1022419 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0001

Data Index: 237497 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0001

Data Index: 609907 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0001

Data Index: 181569 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0165. Min Act: -0.0001

Data Index: 573786 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0164. Min Act: -0.0001

Data Index: 759711 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1600877 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1220073 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0161. Min Act: -0.0001

Data Index: 477383 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0161. Min Act: -0.0001

Data Index: 597955 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1026748 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1290466 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0157. Min Act: -0.0001

Data Index: 162901 (C4 (Web Text))

Max Activating Token Index: 842