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

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

Neuron 1771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0126. Min Range: -5.0126

Max Act: 5.0126. Min Act: -0.0001

Data Index: 503738 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.6854. Min Act: -0.0001

Data Index: 481593 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.7683. Min Act: -0.0001

Data Index: 507049 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.3974. Min Act: -0.0001

Data Index: 1298523 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.0846. Min Act: -0.0000

Data Index: 1354485 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.1498. Min Act: -0.0001

Data Index: 9254 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.1250. Min Act: -0.0001

Data Index: 796488 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.2534. Min Act: -0.0000

Data Index: 119475 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.9110. Min Act: -0.0001

Data Index: 243084 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.0356. Min Act: -0.0001

Data Index: 615756 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.9744. Min Act: -0.0001

Data Index: 593029 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.7918. Min Act: -0.0001

Data Index: 131630 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.0344. Min Act: -0.0000

Data Index: 882976 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.7397. Min Act: -0.0001

Data Index: 1146517 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 5.0126. Min Range: -5.0126

Max Act: 3.0159. Min Act: -0.0001

Data Index: 816556 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.8544. Min Act: -0.0001

Data Index: 357772 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.8412. Min Act: -0.0001

Data Index: 705754 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.9881. Min Act: -0.0001

Data Index: 329476 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.7027. Min Act: -0.0001

Data Index: 1004364 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 5.0126. Min Range: -5.0126

Max Act: 2.9674. Min Act: -0.0001

Data Index: 743357 (C4 (Web Text))

Max Activating Token Index: 539