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

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

Neuron 3905 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: 2.8154. Min Range: -2.8154

Max Act: 2.7646. Min Act: -0.0000

Data Index: 846488 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.6617. Min Act: -0.0000

Data Index: 748656 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.8154. Min Act: -0.0000

Data Index: 971340 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.5011. Min Act: -0.0000

Data Index: 824647 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.6271. Min Act: -0.0000

Data Index: 727901 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.7489. Min Act: -0.0000

Data Index: 1110330 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.6936. Min Act: -0.0000

Data Index: 1324522 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3393. Min Act: -0.0000

Data Index: 68393 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.4184. Min Act: -0.0000

Data Index: 248507 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3206. Min Act: -0.0000

Data Index: 295153 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3761. Min Act: -0.0000

Data Index: 734804 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2103. Min Act: -0.0000

Data Index: 1290315 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3779. Min Act: -0.0000

Data Index: 301529 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3266. Min Act: -0.0000

Data Index: 16351 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2327. Min Act: -0.0000

Data Index: 1151989 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2071. Min Act: -0.0001

Data Index: 604218 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1641. Min Act: -0.0000

Data Index: 248445 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2019. Min Act: -0.0000

Data Index: 1304646 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2989. Min Act: -0.0000

Data Index: 27176 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.2837. Min Act: -0.0000

Data Index: 664479 (C4 (Web Text))

Max Activating Token Index: 424