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

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

Neuron 569 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: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1139127 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1327846 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0006

Data Index: 795045 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0006

Data Index: 819504 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1081990 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0006

Data Index: 690709 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1208315 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0187. Min Act: -0.0006

Data Index: 858212 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0180. Min Act: -0.0006

Data Index: 303990 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0006

Data Index: 109452 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0174. Min Act: -0.0006

Data Index: 400745 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1191720 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1246784 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0006

Data Index: 297597 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0170. Min Act: -0.0006

Data Index: 201929 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1173108 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0168. Min Act: -0.0006

Data Index: 319744 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1235950 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0171. Min Act: -0.0006

Data Index: 966539 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1354518 (C4 (Web Text))

Max Activating Token Index: 949