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

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

Neuron 1707 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1592592 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.4983. Min Act: -0.0000

Data Index: 1401625 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.4742. Min Act: -0.0000

Data Index: 700646 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1603028 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1396494 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1371. Min Act: -0.0000

Data Index: 672000 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1525134 (Python Code)

Max Activating Token Index: 422

Text #7

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0787. Min Act: -0.0000

Data Index: 385782 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1525476 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1184460 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1479085 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1590373 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1421710 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0838. Min Act: -0.0000

Data Index: 363383 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1369510 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1597284 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1515345 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9269. Min Act: -0.0000

Data Index: 147151 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.5214. Min Range: -1.5214

Max Act: 0.9870. Min Act: -0.0000

Data Index: 945523 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 1.5214. Min Range: -1.5214

Max Act: 1.0482. Min Act: -0.0000

Data Index: 706290 (C4 (Web Text))

Max Activating Token Index: 928