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

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

Neuron 1927 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.8988. Min Act: -0.0000

Data Index: 1252169 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.8041. Min Act: -0.0000

Data Index: 554640 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.8260. Min Act: -0.0000

Data Index: 424427 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.6947. Min Act: -0.0000

Data Index: 688144 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.6054. Min Act: 0.0000

Data Index: 811681 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.5754. Min Act: -0.0000

Data Index: 459559 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.5790. Min Act: -0.0000

Data Index: 684802 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.5347. Min Act: -0.0000

Data Index: 54238 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.5478. Min Act: 0.0000

Data Index: 790712 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4328. Min Act: 0.0001

Data Index: 38057 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4207. Min Act: -0.0000

Data Index: 281213 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.5051. Min Act: 0.0001

Data Index: 1046606 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4947. Min Act: -0.0000

Data Index: 894464 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4074. Min Act: 0.0000

Data Index: 471600 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1010235 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4382. Min Act: 0.0001

Data Index: 1038061 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.4320. Min Act: -0.0000

Data Index: 908678 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.3397. Min Act: 0.0000

Data Index: 1068648 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.3191. Min Act: 0.0000

Data Index: 329075 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 1.8988. Min Range: -1.8988

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1020330 (C4 (Web Text))

Max Activating Token Index: 889