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

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

Neuron 3673 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.2559. Min Act: -0.0001

Data Index: 113264 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 4.3234. Min Range: -4.3234

Max Act: 4.3234. Min Act: -0.0001

Data Index: 1025160 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8753. Min Act: -0.0001

Data Index: 7490 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.8130. Min Act: -0.0001

Data Index: 256336 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.9537. Min Act: -0.0001

Data Index: 1116714 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.7881. Min Act: -0.0001

Data Index: 473196 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.3717. Min Act: -0.0001

Data Index: 390821 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.4183. Min Act: -0.0001

Data Index: 1006113 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.2258. Min Act: -0.0001

Data Index: 216647 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.6640. Min Act: -0.0001

Data Index: 588672 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.3172. Min Act: -0.0001

Data Index: 449749 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.1945. Min Act: -0.0001

Data Index: 711708 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.1745. Min Act: -0.0001

Data Index: 495986 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.1807. Min Act: -0.0001

Data Index: 356740 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.1738. Min Act: -0.0001

Data Index: 661831 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.1783. Min Act: -0.0001

Data Index: 1156306 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.3076. Min Act: -0.0001

Data Index: 1321973 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.0000. Min Act: -0.0001

Data Index: 281397 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 4.3234. Min Range: -4.3234

Max Act: 2.9257. Min Act: -0.0001

Data Index: 1110697 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 4.3234. Min Range: -4.3234

Max Act: 3.0551. Min Act: -0.0001

Data Index: 1304134 (C4 (Web Text))

Max Activating Token Index: 928