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

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

Neuron 67 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0364. Min Range: -1.0364

Max Act: 1.0364. Min Act: -0.0000

Data Index: 905854 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8658. Min Act: -0.0000

Data Index: 340717 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1163101 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7747. Min Act: -0.0000

Data Index: 205867 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8420. Min Act: -0.0000

Data Index: 748187 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1192762 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1298854 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8082. Min Act: -0.0000

Data Index: 607062 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7726. Min Act: -0.0000

Data Index: 313247 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8084. Min Act: -0.0000

Data Index: 942259 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8016. Min Act: -0.0000

Data Index: 572920 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8240. Min Act: -0.0000

Data Index: 376689 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7562. Min Act: -0.0000

Data Index: 342403 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.8560. Min Act: -0.0000

Data Index: 711116 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7585. Min Act: -0.0000

Data Index: 678148 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7124. Min Act: -0.0000

Data Index: 157414 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1148131 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7177. Min Act: -0.0000

Data Index: 78874 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1122504 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.0364. Min Range: -1.0364

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1343857 (C4 (Web Text))

Max Activating Token Index: 88