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

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

Neuron 4686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7192. Min Act: -0.0000

Data Index: 394163 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7328. Min Act: -0.0000

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6905. Min Act: -0.0000

Data Index: 340283 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7043. Min Act: -0.0000

Data Index: 701447 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1041089 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6232. Min Act: -0.0000

Data Index: 450521 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1337624 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6506. Min Act: -0.0000

Data Index: 905924 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1205060 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1056838 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6762. Min Act: -0.0000

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6495. Min Act: -0.0000

Data Index: 813569 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6651. Min Act: -0.0000

Data Index: 689610 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6411. Min Act: -0.0000

Data Index: 335070 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6376. Min Act: -0.0000

Data Index: 453833 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6497. Min Act: -0.0000

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1327478 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5862. Min Act: -0.0000

Data Index: 608101 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.5820. Min Act: -0.0000

Data Index: 262582 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.7328. Min Range: -0.7328

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1055221 (C4 (Web Text))

Max Activating Token Index: 301