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

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

Neuron 158 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: 0.4742. Min Range: -0.4742

Max Act: 0.4742. Min Act: -0.0000

Data Index: 57908 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4437. Min Act: -0.0000

Data Index: 642607 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4106. Min Act: -0.0000

Data Index: 810221 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3835. Min Act: -0.0000

Data Index: 552978 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3693. Min Act: -0.0000

Data Index: 13571 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3699. Min Act: -0.0000

Data Index: 80205 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3904. Min Act: -0.0000

Data Index: 361918 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3559. Min Act: -0.0000

Data Index: 636134 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3576. Min Act: -0.0000

Data Index: 879576 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3504. Min Act: -0.0000

Data Index: 508477 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3396. Min Act: -0.0000

Data Index: 727005 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1112725 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1336454 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3262. Min Act: -0.0000

Data Index: 340111 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1084538 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3354. Min Act: -0.0000

Data Index: 871951 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3425. Min Act: -0.0000

Data Index: 39730 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1229087 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1215938 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1201193 (C4 (Web Text))

Max Activating Token Index: 640