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

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

Neuron 471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1324. Min Range: -2.1324

Max Act: 2.1324. Min Act: 0.0000

Data Index: 1192071 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 2.1324. Min Range: -2.1324

Max Act: 2.1108. Min Act: -0.0000

Data Index: 1248967 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1260922 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1274748 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.4934. Min Act: -0.0000

Data Index: 297819 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1253403 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.4692. Min Act: -0.0000

Data Index: 926060 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1186866 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.4245. Min Act: -0.0000

Data Index: 609728 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.2227. Min Act: -0.0000

Data Index: 789909 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.3021. Min Act: -0.0000

Data Index: 489565 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.2257. Min Act: -0.0000

Data Index: 875744 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1316415 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.1416. Min Act: -0.0000

Data Index: 829590 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.2067. Min Act: -0.0000

Data Index: 557761 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.1587. Min Act: -0.0000

Data Index: 877389 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.2166. Min Act: -0.0000

Data Index: 237201 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.1127. Min Act: 0.0001

Data Index: 216790 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.0968. Min Act: 0.0001

Data Index: 1201547 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 2.1324. Min Range: -2.1324

Max Act: 1.0898. Min Act: -0.0001

Data Index: 1292436 (C4 (Web Text))

Max Activating Token Index: 417