Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0003

Data Index: 580078 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0562. Min Act: -0.0004

Data Index: 1053958 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0537. Min Act: -0.0003

Data Index: 453381 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1200398 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0517. Min Act: -0.0003

Data Index: 128599 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0520. Min Act: -0.0003

Data Index: 329709 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0490. Min Act: -0.0003

Data Index: 624186 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0501. Min Act: -0.0003

Data Index: 441721 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0479. Min Act: -0.0003

Data Index: 546477 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0474. Min Act: -0.0004

Data Index: 81074 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0464. Min Act: -0.0004

Data Index: 470675 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0004

Data Index: 906969 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0462. Min Act: -0.0003

Data Index: 952383 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0003

Data Index: 118539 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1050844 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0003

Data Index: 141905 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0455. Min Act: -0.0004

Data Index: 24370 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0469. Min Act: -0.0003

Data Index: 574135 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0448. Min Act: -0.0003

Data Index: 769031 (C4 (Web Text))

Max Activating Token Index: 265