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

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

Neuron 4261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4202. Min Range: -5.4202

Max Act: 5.4202. Min Act: -0.0000

Data Index: 1273674 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.5306. Min Act: -0.0000

Data Index: 574448 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.3385. Min Act: -0.0000

Data Index: 1200763 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.1848. Min Act: -0.0000

Data Index: 477862 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.2004. Min Act: -0.0000

Data Index: 1341143 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.0310. Min Act: -0.0000

Data Index: 1043664 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.0276. Min Act: -0.0000

Data Index: 835181 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.8840. Min Act: -0.0000

Data Index: 340738 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.8635. Min Act: -0.0000

Data Index: 671991 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.8624. Min Act: -0.0000

Data Index: 337796 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.1653. Min Act: -0.0000

Data Index: 294117 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.1597. Min Act: -0.0000

Data Index: 581997 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.1713. Min Act: -0.0000

Data Index: 424884 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.9898. Min Act: -0.0000

Data Index: 629192 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.9593. Min Act: -0.0000

Data Index: 466049 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.1331. Min Act: -0.0000

Data Index: 1180163 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.0702. Min Act: -0.0000

Data Index: 505758 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.0273. Min Act: -0.0000

Data Index: 107828 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 5.4202. Min Range: -5.4202

Max Act: 4.0204. Min Act: -0.0000

Data Index: 118027 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 5.4202. Min Range: -5.4202

Max Act: 3.8618. Min Act: -0.0000

Data Index: 646489 (C4 (Web Text))

Max Activating Token Index: 578