Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 904 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.8386. Min Act: -0.0000

Data Index: 71134 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.8264. Min Act: -0.0000

Data Index: 907523 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.7965. Min Act: -0.0000

Data Index: 69676 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.6374. Min Act: -0.0000

Data Index: 376459 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4851. Min Act: -0.0000

Data Index: 40659 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1306493 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.5175. Min Act: -0.0000

Data Index: 770088 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.1781. Min Act: -0.0000

Data Index: 147424 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4202. Min Act: 0.0000

Data Index: 1338914 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3896. Min Act: -0.0000

Data Index: 808612 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3796. Min Act: -0.0000

Data Index: 593934 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2946. Min Act: -0.0000

Data Index: 360912 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3306. Min Act: -0.0000

Data Index: 700209 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1035641 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3184. Min Act: -0.0000

Data Index: 403894 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1199658 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3315. Min Act: -0.0000

Data Index: 701233 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2933. Min Act: -0.0000

Data Index: 483640 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3411. Min Act: -0.0000

Data Index: 659298 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3210. Min Act: -0.0000

Data Index: 873933 (C4 (Web Text))

Max Activating Token Index: 80