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

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

Neuron 4327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3768. Min Act: -0.0000

Data Index: 984574 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1101086 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3168. Min Act: -0.0000

Data Index: 186321 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3241. Min Act: -0.0000

Data Index: 680026 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3304. Min Act: -0.0000

Data Index: 262523 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1302407 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2766. Min Act: -0.0000

Data Index: 621918 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1353993 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2642. Min Act: -0.0000

Data Index: 133212 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2502. Min Act: -0.0000

Data Index: 920945 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2588. Min Act: -0.0000

Data Index: 412398 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2636. Min Act: -0.0000

Data Index: 556210 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2695. Min Act: -0.0000

Data Index: 134080 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1200347 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1064482 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2448. Min Act: -0.0000

Data Index: 186582 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1356466 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1159840 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2460. Min Act: -0.0000

Data Index: 339650 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2356. Min Act: -0.0000

Data Index: 549749 (C4 (Web Text))

Max Activating Token Index: 948