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

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

Neuron 3254 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: 0.1637. Min Range: -0.1637

Max Act: 0.1637. Min Act: -0.0000

Data Index: 329139 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1335. Min Act: -0.0001

Data Index: 365656 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1005417 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1582. Min Act: -0.0001

Data Index: 557297 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1296. Min Act: -0.0001

Data Index: 397866 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1276. Min Act: -0.0000

Data Index: 86492 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1219. Min Act: -0.0001

Data Index: 793858 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1149. Min Act: -0.0000

Data Index: 427847 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1176. Min Act: -0.0000

Data Index: 375223 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1216. Min Act: -0.0001

Data Index: 845376 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1216. Min Act: -0.0001

Data Index: 654201 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1075. Min Act: -0.0001

Data Index: 729983 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1126. Min Act: -0.0001

Data Index: 129180 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1200. Min Act: -0.0001

Data Index: 47008 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1129. Min Act: -0.0000

Data Index: 503914 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1169. Min Act: -0.0001

Data Index: 428192 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1312085 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1160. Min Act: -0.0000

Data Index: 151633 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1139. Min Act: -0.0000

Data Index: 210247 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.1637. Min Range: -0.1637

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1124318 (C4 (Web Text))

Max Activating Token Index: 690