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

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

Neuron 3921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1292186 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1287. Min Act: -0.0001

Data Index: 521910 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1298. Min Act: -0.0001

Data Index: 351167 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1342. Min Act: -0.0001

Data Index: 764905 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1270. Min Act: -0.0001

Data Index: 786917 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1199. Min Act: -0.0001

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1175. Min Act: -0.0001

Data Index: 122589 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1208450 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1164. Min Act: -0.0001

Data Index: 997124 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1151. Min Act: -0.0001

Data Index: 445637 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1198. Min Act: -0.0001

Data Index: 777002 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1138. Min Act: -0.0000

Data Index: 187272 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1261374 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1043005 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0965. Min Act: -0.0001

Data Index: 529154 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1035. Min Act: -0.0000

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0999. Min Act: -0.0001

Data Index: 60913 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0964. Min Act: -0.0001

Data Index: 700370 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.0986. Min Act: -0.0000

Data Index: 963942 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.1342. Min Range: -0.1342

Max Act: 0.1079. Min Act: -0.0001

Data Index: 498046 (C4 (Web Text))

Max Activating Token Index: 271