Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1358 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0486. Min Act: -0.0003

Data Index: 643712 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0003

Data Index: 892221 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0503. Min Act: -0.0003

Data Index: 216257 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0453. Min Act: -0.0003

Data Index: 279099 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1266144 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1183916 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0466. Min Act: -0.0003

Data Index: 380910 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1304787 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0480. Min Act: -0.0003

Data Index: 998811 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0468. Min Act: -0.0003

Data Index: 576226 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1258026 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0448. Min Act: -0.0003

Data Index: 955047 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0457. Min Act: -0.0003

Data Index: 524898 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0437. Min Act: -0.0003

Data Index: 969005 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1295078 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0432. Min Act: -0.0003

Data Index: 507975 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0415. Min Act: -0.0003

Data Index: 403412 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0439. Min Act: -0.0003

Data Index: 935348 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0420. Min Act: -0.0003

Data Index: 721700 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0407. Min Act: -0.0003

Data Index: 26417 (C4 (Web Text))

Max Activating Token Index: 694