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

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

Neuron 5939 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1313937 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0001

Data Index: 407654 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1006071 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0446. Min Act: -0.0001

Data Index: 86676 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0519. Min Act: -0.0001

Data Index: 436600 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1377351 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0409. Min Act: -0.0001

Data Index: 717176 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0384. Min Act: -0.0001

Data Index: 18044 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0337. Min Act: -0.0001

Data Index: 298700 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0310. Min Act: -0.0001

Data Index: 564259 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0321. Min Act: -0.0002

Data Index: 530593 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0349. Min Act: -0.0001

Data Index: 236897 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1305347 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0335. Min Act: -0.0001

Data Index: 545196 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0256. Min Act: -0.0001

Data Index: 780135 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0273. Min Act: -0.0001

Data Index: 35087 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0263. Min Act: -0.0001

Data Index: 146318 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1255463 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0259. Min Act: -0.0002

Data Index: 120631 (C4 (Web Text))

Max Activating Token Index: 580