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

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

Neuron 2486 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: 0.6335. Min Range: -0.6335

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1320592 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5374. Min Act: -0.0000

Data Index: 858991 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5239. Min Act: 0.0000

Data Index: 181622 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.5226. Min Act: -0.0001

Data Index: 328117 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4903. Min Act: -0.0000

Data Index: 721053 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1067353 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4838. Min Act: -0.0000

Data Index: 862274 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4775. Min Act: -0.0000

Data Index: 711117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4759. Min Act: -0.0001

Data Index: 1187403 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4702. Min Act: -0.0001

Data Index: 489021 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1028581 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4444. Min Act: -0.0000

Data Index: 765115 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4412. Min Act: -0.0000

Data Index: 540755 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4495. Min Act: -0.0000

Data Index: 577432 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4322. Min Act: -0.0000

Data Index: 441121 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4289. Min Act: 0.0000

Data Index: 1109995 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1034201 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4445. Min Act: -0.0000

Data Index: 37120 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4420. Min Act: 0.0000

Data Index: 1151221 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.6335. Min Range: -0.6335

Max Act: 0.4281. Min Act: -0.0000

Data Index: 686873 (C4 (Web Text))

Max Activating Token Index: 810