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

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

Neuron 3753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1844. Min Range: -1.1844

Max Act: 1.1844. Min Act: -0.0000

Data Index: 609137 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.1844. Min Range: -1.1844

Max Act: 1.0688. Min Act: -0.0000

Data Index: 135433 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.1844. Min Range: -1.1844

Max Act: 1.0250. Min Act: -0.0000

Data Index: 896690 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1330524 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8911. Min Act: -0.0000

Data Index: 484677 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1028046 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9587. Min Act: -0.0000

Data Index: 79068 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1082389 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8628. Min Act: -0.0000

Data Index: 15809 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9788. Min Act: -0.0000

Data Index: 219129 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9054. Min Act: -0.0000

Data Index: 275214 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8575. Min Act: -0.0000

Data Index: 735600 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.9132. Min Act: -0.0000

Data Index: 408040 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8421. Min Act: -0.0000

Data Index: 820729 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.7486. Min Act: -0.0000

Data Index: 343420 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8288. Min Act: -0.0000

Data Index: 849493 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1195588 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.7208. Min Act: -0.0000

Data Index: 303390 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.8163. Min Act: -0.0000

Data Index: 833710 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.1844. Min Range: -1.1844

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1215885 (C4 (Web Text))

Max Activating Token Index: 364