Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3881 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0003

Data Index: 908535 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1502244 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1029844 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1132765 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0459. Min Act: -0.0003

Data Index: 184213 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1485589 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0422. Min Act: -0.0003

Data Index: 649818 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1423123 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1392509 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1517163 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1617047 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1465353 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1606394 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0420. Min Act: -0.0003

Data Index: 348103 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1430349 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0422. Min Act: -0.0003

Data Index: 756955 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0421. Min Act: -0.0003

Data Index: 449925 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1639034 (Python Code)

Max Activating Token Index: 491

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0375. Min Act: -0.0003

Data Index: 66918 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1628383 (Python Code)

Max Activating Token Index: 566