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

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

Neuron 3603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1150350 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1716 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2872. Min Act: -0.0000

Data Index: 38103 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2844. Min Act: -0.0000

Data Index: 761042 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1164696 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1019121 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1206599 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2516. Min Act: -0.0000

Data Index: 709607 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2289. Min Act: -0.0000

Data Index: 187772 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2312. Min Act: -0.0000

Data Index: 801550 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2339. Min Act: -0.0000

Data Index: 4681 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2388. Min Act: -0.0000

Data Index: 582110 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1353338 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1004943 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2197. Min Act: -0.0000

Data Index: 466040 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2262. Min Act: -0.0000

Data Index: 273504 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2109. Min Act: -0.0000

Data Index: 250126 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2159. Min Act: -0.0000

Data Index: 829599 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2221. Min Act: -0.0000

Data Index: 305901 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1014881 (C4 (Web Text))

Max Activating Token Index: 961