Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1157517 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1613381 (Python Code)

Max Activating Token Index: 496

Text #2

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1539427 (Python Code)

Max Activating Token Index: 693

Text #3

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.3024. Min Act: -0.0000

Data Index: 494055 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2619. Min Act: -0.0000

Data Index: 760603 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1484815 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1615521 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1494518 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1388422 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2459. Min Act: -0.0000

Data Index: 723664 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1408906 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1585915 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1653298 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1508386 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1424028 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1094221 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1459011 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1129050 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2336. Min Act: -0.0000

Data Index: 806860 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.4015. Min Range: -0.4015

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1084099 (C4 (Web Text))

Max Activating Token Index: 526