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

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

Neuron 1995 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: 0.3076. Min Range: -0.3076

Max Act: 0.3052. Min Act: -0.0001

Data Index: 384691 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.3076. Min Act: -0.0000

Data Index: 54386 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2838. Min Act: -0.0001

Data Index: 364287 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2815. Min Act: -0.0001

Data Index: 298242 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2635. Min Act: -0.0000

Data Index: 619104 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2399. Min Act: -0.0001

Data Index: 59254 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1064786 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2320. Min Act: -0.0000

Data Index: 657557 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2210. Min Act: -0.0001

Data Index: 846397 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2324. Min Act: -0.0001

Data Index: 316219 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2320. Min Act: -0.0000

Data Index: 597650 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1139452 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2099. Min Act: -0.0001

Data Index: 436770 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2388. Min Act: -0.0000

Data Index: 793380 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2213. Min Act: -0.0001

Data Index: 345231 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1190841 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.1959. Min Act: -0.0000

Data Index: 607263 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2012. Min Act: -0.0001

Data Index: 206687 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1163245 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.3076. Min Range: -0.3076

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1227907 (C4 (Web Text))

Max Activating Token Index: 15