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

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

Neuron 1649 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5884. Min Act: -0.0000

Data Index: 605201 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5863. Min Act: -0.0000

Data Index: 951643 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5814. Min Act: -0.0000

Data Index: 215549 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5360. Min Act: -0.0000

Data Index: 44112 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5392. Min Act: -0.0000

Data Index: 931911 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5026. Min Act: -0.0000

Data Index: 193897 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4873. Min Act: -0.0000

Data Index: 43458 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4854. Min Act: -0.0000

Data Index: 302717 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5126. Min Act: -0.0000

Data Index: 762253 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4667. Min Act: -0.0000

Data Index: 396317 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4845. Min Act: -0.0000

Data Index: 781210 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1028009 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4597. Min Act: -0.0000

Data Index: 553456 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1203125 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4753. Min Act: -0.0000

Data Index: 540255 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4571. Min Act: -0.0000

Data Index: 833913 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4532. Min Act: -0.0000

Data Index: 523828 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4485. Min Act: -0.0000

Data Index: 754362 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4370. Min Act: -0.0000

Data Index: 458625 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4341. Min Act: -0.0000

Data Index: 294016 (C4 (Web Text))

Max Activating Token Index: 930