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

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

Neuron 3061 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: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1529716 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1427825 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1563844 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1476451 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1461848 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1607435 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1415497 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1577292 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1396498 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1402377 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1442761 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1493448 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1406556 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1652401 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1391992 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1492212 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1625146 (Python Code)

Max Activating Token Index: 545

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1455010 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1547281 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1527292 (Python Code)

Max Activating Token Index: 30