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

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

Neuron 4868 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1268. Min Range: -2.1268

Max Act: 2.1268. Min Act: -0.0000

Data Index: 189218 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.1268. Min Range: -2.1268

Max Act: 2.0322. Min Act: -0.0000

Data Index: 1312514 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.7016. Min Act: -0.0000

Data Index: 1308045 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.7397. Min Act: -0.0000

Data Index: 88368 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.7138. Min Act: -0.0000

Data Index: 180802 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.8373. Min Act: -0.0000

Data Index: 365350 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.7726. Min Act: -0.0000

Data Index: 362187 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1090704 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.6798. Min Act: -0.0000

Data Index: 143965 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5984. Min Act: -0.0000

Data Index: 834361 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.6421. Min Act: -0.0000

Data Index: 658145 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5809. Min Act: -0.0000

Data Index: 1041952 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.6261. Min Act: -0.0000

Data Index: 658363 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5703. Min Act: -0.0000

Data Index: 303673 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5973. Min Act: -0.0000

Data Index: 121737 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5633. Min Act: -0.0000

Data Index: 949423 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5262. Min Act: -0.0000

Data Index: 764026 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5266. Min Act: -0.0000

Data Index: 4909 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.4374. Min Act: -0.0000

Data Index: 462059 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 2.1268. Min Range: -2.1268

Max Act: 1.5218. Min Act: -0.0000

Data Index: 113965 (C4 (Web Text))

Max Activating Token Index: 100