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

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

Neuron 1501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9572. Min Act: -0.0000

Data Index: 928878 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1193347 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1316096 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8642. Min Act: -0.0000

Data Index: 703904 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8645. Min Act: -0.0000

Data Index: 436630 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8616. Min Act: -0.0000

Data Index: 782397 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8604. Min Act: -0.0000

Data Index: 810236 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8589. Min Act: -0.0000

Data Index: 207450 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8257. Min Act: -0.0000

Data Index: 834832 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8471. Min Act: -0.0000

Data Index: 898859 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8226. Min Act: -0.0000

Data Index: 488411 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8421. Min Act: -0.0000

Data Index: 260808 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1214847 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7923. Min Act: -0.0000

Data Index: 156044 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1267604 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7772. Min Act: -0.0000

Data Index: 998437 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.7331. Min Act: -0.0000

Data Index: 839045 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6895. Min Act: -0.0000

Data Index: 761964 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.8026. Min Act: -0.0000

Data Index: 752511 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.9572. Min Range: -0.9572

Max Act: 0.6971. Min Act: -0.0000

Data Index: 491544 (C4 (Web Text))

Max Activating Token Index: 217