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

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

Neuron 2225 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.3337. Min Act: -0.0000

Data Index: 1571139 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.2573. Min Act: -0.0000

Data Index: 1649782 (Python Code)

Max Activating Token Index: 502

Text #2

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.2302. Min Act: -0.0000

Data Index: 1397300 (Python Code)

Max Activating Token Index: 685

Text #3

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0897. Min Act: -0.0000

Data Index: 1441705 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.2047. Min Act: -0.0000

Data Index: 1382814 (Python Code)

Max Activating Token Index: 450

Text #5

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0340. Min Act: -0.0000

Data Index: 1649323 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.1192. Min Act: -0.0000

Data Index: 1487829 (Python Code)

Max Activating Token Index: 777

Text #7

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0906. Min Act: -0.0000

Data Index: 1571870 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.2210. Min Act: -0.0000

Data Index: 1648655 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.8506. Min Act: -0.0000

Data Index: 1555598 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1485217 (Python Code)

Max Activating Token Index: 610

Text #11

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0325. Min Act: -0.0000

Data Index: 1393642 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0236. Min Act: -0.0000

Data Index: 1490941 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.8842. Min Act: -0.0000

Data Index: 1551358 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1547783 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.9742. Min Act: -0.0000

Data Index: 1478723 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.9702. Min Act: -0.0000

Data Index: 1529863 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.8497. Min Act: -0.0000

Data Index: 1554453 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 2.3337. Min Range: -2.3337

Max Act: 2.0238. Min Act: -0.0001

Data Index: 1488950 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 2.3337. Min Range: -2.3337

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1430574 (Python Code)

Max Activating Token Index: 769