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

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

Neuron 2127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1955. Min Act: -0.0001

Data Index: 389617 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1412. Min Act: -0.0001

Data Index: 298896 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1359. Min Act: -0.0001

Data Index: 712505 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1302. Min Act: -0.0001

Data Index: 749102 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1252. Min Act: -0.0001

Data Index: 438641 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1242821 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1178. Min Act: -0.0001

Data Index: 856392 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1205. Min Act: -0.0001

Data Index: 940845 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1013160 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1234. Min Act: -0.0001

Data Index: 304625 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1142. Min Act: -0.0001

Data Index: 188990 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1185. Min Act: -0.0001

Data Index: 565504 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1163. Min Act: -0.0001

Data Index: 14359 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1157. Min Act: -0.0001

Data Index: 46836 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1148. Min Act: -0.0001

Data Index: 740096 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1349613 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1010502 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1143. Min Act: -0.0001

Data Index: 11327 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1100. Min Act: -0.0001

Data Index: 753435 (C4 (Web Text))

Max Activating Token Index: 987