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

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

Neuron 4307 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: 1.1347. Min Range: -1.1347

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1353603 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.9478. Min Act: -0.0000

Data Index: 978361 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8995. Min Act: -0.0000

Data Index: 498795 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1073282 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8011. Min Act: -0.0000

Data Index: 261388 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8461. Min Act: -0.0000

Data Index: 763789 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1230676 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8346. Min Act: -0.0000

Data Index: 371693 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8277. Min Act: -0.0000

Data Index: 818534 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8065. Min Act: -0.0000

Data Index: 256268 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8069. Min Act: -0.0000

Data Index: 345618 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8309. Min Act: -0.0000

Data Index: 387100 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8273. Min Act: -0.0000

Data Index: 963136 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1222160 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.7967. Min Act: -0.0000

Data Index: 352212 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.7918. Min Act: -0.0000

Data Index: 430717 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1220117 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.8072. Min Act: -0.0000

Data Index: 720723 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.7783. Min Act: -0.0000

Data Index: 812097 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.1347. Min Range: -1.1347

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1096832 (C4 (Web Text))

Max Activating Token Index: 735