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

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

Neuron 4255 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.2146. Min Range: -11.2146

Max Act: 11.2146. Min Act: -0.0000

Data Index: 1034661 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.3804. Min Act: -0.0000

Data Index: 367092 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1113340 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1289038 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1304631 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1247. Min Act: -0.0000

Data Index: 553280 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1402722 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1509626 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1214207 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0891. Min Act: -0.0000

Data Index: 634833 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1113. Min Act: -0.0000

Data Index: 49306 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.1170. Min Act: -0.0000

Data Index: 576226 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0948. Min Act: 0.0001

Data Index: 1044483 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0938. Min Act: -0.0000

Data Index: 312261 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0875. Min Act: -0.0000

Data Index: 852850 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1133798 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1065143 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 11.2146. Min Range: -11.2146

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1273235 (C4 (Web Text))

Max Activating Token Index: 972