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

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

Neuron 1300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1109231 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1037636 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0462. Min Act: -0.0003

Data Index: 950311 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0445. Min Act: -0.0003

Data Index: 217625 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0444. Min Act: -0.0003

Data Index: 161457 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0452. Min Act: -0.0002

Data Index: 786260 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1333783 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0433. Min Act: -0.0003

Data Index: 816808 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0436. Min Act: -0.0002

Data Index: 519850 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0426. Min Act: -0.0003

Data Index: 72390 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1471636 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0408. Min Act: -0.0003

Data Index: 68032 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0389. Min Act: -0.0003

Data Index: 908826 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0420. Min Act: -0.0002

Data Index: 193920 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0408. Min Act: -0.0003

Data Index: 130830 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0391. Min Act: -0.0003

Data Index: 988573 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0378. Min Act: -0.0003

Data Index: 17146 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1037044 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1248521 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1277177 (C4 (Web Text))

Max Activating Token Index: 329