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

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

Neuron 1591 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: 0.5635. Min Range: -0.5635

Max Act: 0.5635. Min Act: -0.0000

Data Index: 970735 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1268071 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1140047 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1069046 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1174558 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4761. Min Act: -0.0000

Data Index: 893856 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1111284 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1085652 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4319. Min Act: -0.0000

Data Index: 45898 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3791. Min Act: -0.0000

Data Index: 943522 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1234457 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3897. Min Act: -0.0000

Data Index: 540041 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3962. Min Act: -0.0000

Data Index: 289169 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1067085 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3684. Min Act: -0.0000

Data Index: 392289 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3578. Min Act: -0.0000

Data Index: 250917 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3579. Min Act: -0.0000

Data Index: 288364 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1217249 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1248556 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3123. Min Act: -0.0000

Data Index: 270072 (C4 (Web Text))

Max Activating Token Index: 127