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

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

Neuron 536 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: 5.2893. Min Range: -5.2893

Max Act: 5.2893. Min Act: -0.0000

Data Index: 994945 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 5.2893. Min Range: -5.2893

Max Act: 5.0670. Min Act: -0.0000

Data Index: 852729 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.9016. Min Act: -0.0000

Data Index: 875868 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 5.2893. Min Range: -5.2893

Max Act: 5.0400. Min Act: -0.0000

Data Index: 946640 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.7937. Min Act: -0.0000

Data Index: 616518 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.5426. Min Act: -0.0000

Data Index: 180942 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.6066. Min Act: -0.0000

Data Index: 729621 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.6638. Min Act: -0.0000

Data Index: 657901 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.3293. Min Act: -0.0000

Data Index: 159339 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.3845. Min Act: -0.0000

Data Index: 1316155 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.3882. Min Act: -0.0000

Data Index: 1105780 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.7423. Min Act: -0.0000

Data Index: 1270866 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.2709. Min Act: -0.0000

Data Index: 672234 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.1181. Min Act: -0.0000

Data Index: 851113 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.1127. Min Act: -0.0000

Data Index: 831429 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 5.2893. Min Range: -5.2893

Max Act: 4.2942. Min Act: -0.0000

Data Index: 351946 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 5.2893. Min Range: -5.2893

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1245002 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 5.2893. Min Range: -5.2893

Max Act: 3.8127. Min Act: -0.0000

Data Index: 525784 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 5.2893. Min Range: -5.2893

Max Act: 3.8772. Min Act: -0.0000

Data Index: 1064668 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 5.2893. Min Range: -5.2893

Max Act: 3.9269. Min Act: -0.0000

Data Index: 889706 (C4 (Web Text))

Max Activating Token Index: 570