Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2874 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1093928 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.3011. Min Act: -0.0000

Data Index: 138160 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1106183 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2668. Min Act: -0.0000

Data Index: 340430 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1222057 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2797. Min Act: -0.0000

Data Index: 1199292 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2588. Min Act: -0.0000

Data Index: 565278 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2449. Min Act: -0.0000

Data Index: 592176 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2516. Min Act: 0.0000

Data Index: 578652 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2452. Min Act: -0.0000

Data Index: 155221 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2303. Min Act: -0.0000

Data Index: 324563 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2216. Min Act: -0.0000

Data Index: 292190 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2220. Min Act: -0.0000

Data Index: 160279 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1576579 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2209. Min Act: -0.0000

Data Index: 327354 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2177. Min Act: -0.0000

Data Index: 995595 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2187. Min Act: -0.0000

Data Index: 794697 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2252. Min Act: -0.0000

Data Index: 890007 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2324. Min Act: -0.0000

Data Index: 912746 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1614571 (Python Code)

Max Activating Token Index: 706