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

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

Neuron 4739 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 500706 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0539. Min Act: -0.0002

Data Index: 33835 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0002

Data Index: 695659 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1076428 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0461. Min Act: -0.0002

Data Index: 289485 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1200865 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0457. Min Act: -0.0001

Data Index: 104980 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0455. Min Act: -0.0001

Data Index: 645957 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0455. Min Act: -0.0002

Data Index: 155179 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1200638 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1181724 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1105948 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0429. Min Act: -0.0002

Data Index: 170573 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0428. Min Act: -0.0002

Data Index: 471086 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0428. Min Act: -0.0002

Data Index: 790648 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1350502 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1137799 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0423. Min Act: -0.0002

Data Index: 401724 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0420. Min Act: -0.0001

Data Index: 152228 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0419. Min Act: -0.0002

Data Index: 778649 (C4 (Web Text))

Max Activating Token Index: 11