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

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

Neuron 2446 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: 0.9425. Min Range: -0.9425

Max Act: 0.9425. Min Act: -0.0001

Data Index: 429107 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9219. Min Act: -0.0001

Data Index: 1114009 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8503. Min Act: -0.0001

Data Index: 1294209 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8318. Min Act: -0.0001

Data Index: 1283852 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8250. Min Act: -0.0001

Data Index: 24291 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7732. Min Act: -0.0001

Data Index: 854328 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8172. Min Act: -0.0001

Data Index: 199306 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8076. Min Act: -0.0001

Data Index: 1241051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7586. Min Act: -0.0001

Data Index: 892341 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7691. Min Act: -0.0000

Data Index: 788625 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7417. Min Act: -0.0001

Data Index: 57780 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8140. Min Act: -0.0001

Data Index: 107747 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1287940 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7540. Min Act: -0.0001

Data Index: 245100 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7487. Min Act: -0.0001

Data Index: 110787 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7076. Min Act: -0.0001

Data Index: 567068 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7513. Min Act: -0.0000

Data Index: 97435 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7400. Min Act: -0.0000

Data Index: 64765 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7160. Min Act: -0.0001

Data Index: 355215 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7207. Min Act: -0.0000

Data Index: 512346 (C4 (Web Text))

Max Activating Token Index: 821