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

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

Neuron 2598 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: 4.1667. Min Range: -4.1667

Max Act: 3.9188. Min Act: -0.0000

Data Index: 1026737 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 4.1667. Min Range: -4.1667

Max Act: 4.1667. Min Act: -0.0000

Data Index: 723321 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8583. Min Act: -0.0000

Data Index: 661902 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.8187. Min Act: -0.0000

Data Index: 593598 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.5805. Min Act: -0.0000

Data Index: 165264 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.5888. Min Act: -0.0000

Data Index: 392584 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.2495. Min Act: -0.0000

Data Index: 404037 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1245. Min Act: -0.0000

Data Index: 1169837 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1284. Min Act: -0.0000

Data Index: 754861 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.2846. Min Act: -0.0000

Data Index: 717123 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1026. Min Act: -0.0000

Data Index: 566941 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.4031. Min Act: -0.0000

Data Index: 899891 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.0340. Min Act: -0.0000

Data Index: 1335455 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.3235. Min Act: -0.0000

Data Index: 181170 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1436. Min Act: -0.0000

Data Index: 267307 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 4.1667. Min Range: -4.1667

Max Act: 2.4870. Min Act: -0.0000

Data Index: 789013 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1611. Min Act: -0.0000

Data Index: 1108132 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.2875. Min Act: -0.0000

Data Index: 1200869 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.1667. Min Range: -4.1667

Max Act: 2.8436. Min Act: -0.0000

Data Index: 703037 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 4.1667. Min Range: -4.1667

Max Act: 3.1021. Min Act: -0.0000

Data Index: 939101 (C4 (Web Text))

Max Activating Token Index: 69