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

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

Neuron 4833 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: 6.1079. Min Range: -6.1079

Max Act: 6.1079. Min Act: -0.0000

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.6666. Min Act: -0.0000

Data Index: 50466 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.3613. Min Act: -0.0000

Data Index: 1155737 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.4014. Min Act: -0.0000

Data Index: 131113 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.3923. Min Act: -0.0000

Data Index: 795120 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.3367. Min Act: -0.0000

Data Index: 1104212 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.0912. Min Act: -0.0000

Data Index: 1130261 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.3436. Min Act: -0.0000

Data Index: 470569 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.1599. Min Act: -0.0000

Data Index: 96535 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.0688. Min Act: -0.0000

Data Index: 33788 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.0337. Min Act: -0.0000

Data Index: 1221464 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.0051. Min Act: -0.0000

Data Index: 333349 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 6.1079. Min Range: -6.1079

Max Act: 5.0359. Min Act: -0.0000

Data Index: 387395 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.8393. Min Act: -0.0000

Data Index: 1217347 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.9263. Min Act: -0.0000

Data Index: 1108638 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.7412. Min Act: -0.0000

Data Index: 886127 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.5315. Min Act: -0.0000

Data Index: 588677 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.6455. Min Act: -0.0000

Data Index: 1006779 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.5593. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 6.1079. Min Range: -6.1079

Max Act: 4.6381. Min Act: -0.0000

Data Index: 1311314 (C4 (Web Text))

Max Activating Token Index: 851