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

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

Neuron 4275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5136. Min Range: -4.5136

Max Act: 4.5136. Min Act: -0.0000

Data Index: 58317 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 4.5136. Min Range: -4.5136

Max Act: 4.0135. Min Act: -0.0000

Data Index: 1122053 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.8843. Min Act: -0.0000

Data Index: 818366 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.6622. Min Act: -0.0000

Data Index: 6357 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.6751. Min Act: -0.0000

Data Index: 676656 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.5552. Min Act: -0.0000

Data Index: 693445 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.4333. Min Act: -0.0000

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.4898. Min Act: -0.0000

Data Index: 1052075 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.2263. Min Act: -0.0000

Data Index: 62114 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.1620. Min Act: -0.0000

Data Index: 1234315 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.0433. Min Act: -0.0001

Data Index: 389148 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.4766. Min Act: -0.0000

Data Index: 694863 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.4661. Min Act: -0.0000

Data Index: 1095589 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.5554. Min Act: -0.0000

Data Index: 49188 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.0118. Min Act: -0.0001

Data Index: 190314 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 4.5136. Min Range: -4.5136

Max Act: 2.8677. Min Act: -0.0000

Data Index: 368590 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 4.5136. Min Range: -4.5136

Max Act: 2.6693. Min Act: -0.0001

Data Index: 1018364 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.2109. Min Act: -0.0000

Data Index: 113686 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.4343. Min Act: -0.0001

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 4.5136. Min Range: -4.5136

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1220336 (C4 (Web Text))

Max Activating Token Index: 116