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

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

Neuron 5005 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3987. Min Act: -0.0000

Data Index: 423615 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3339. Min Act: -0.0000

Data Index: 533837 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3222. Min Act: -0.0000

Data Index: 247374 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.3139. Min Act: -0.0000

Data Index: 895465 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1192231 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2628. Min Act: -0.0000

Data Index: 941844 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2655. Min Act: -0.0000

Data Index: 329678 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2456. Min Act: -0.0000

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2322. Min Act: -0.0000

Data Index: 598158 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2553. Min Act: -0.0000

Data Index: 938089 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2392. Min Act: -0.0000

Data Index: 741675 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2293. Min Act: -0.0000

Data Index: 782657 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1289542 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1078089 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2243. Min Act: -0.0000

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2163. Min Act: -0.0000

Data Index: 963411 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1327916 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1219745 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1357137 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.3987. Min Range: -0.3987

Max Act: 0.2130. Min Act: -0.0000

Data Index: 827290 (C4 (Web Text))

Max Activating Token Index: 224