Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.2474. Min Act: -0.0002

Data Index: 1058633 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.3152. Min Act: -0.0001

Data Index: 86101 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.2590. Min Act: -0.0002

Data Index: 795900 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.2535. Min Act: -0.0002

Data Index: 1291562 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.1090. Min Act: -0.0001

Data Index: 482222 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.1016. Min Act: -0.0001

Data Index: 707839 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0538. Min Act: -0.0002

Data Index: 378135 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0490. Min Act: -0.0002

Data Index: 700143 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0049. Min Act: -0.0001

Data Index: 816886 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0903. Min Act: -0.0001

Data Index: 297204 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0829. Min Act: -0.0002

Data Index: 822492 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0453. Min Act: -0.0002

Data Index: 50967 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0104. Min Act: -0.0001

Data Index: 781262 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9747. Min Act: -0.0002

Data Index: 262556 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0164. Min Act: -0.0001

Data Index: 968394 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0127. Min Act: -0.0002

Data Index: 700702 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0050. Min Act: -0.0002

Data Index: 328887 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0336. Min Act: -0.0001

Data Index: 265502 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.3152. Min Range: -1.3152

Max Act: 1.0349. Min Act: -0.0001

Data Index: 1141580 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.3152. Min Range: -1.3152

Max Act: 0.9758. Min Act: -0.0002

Data Index: 602766 (C4 (Web Text))

Max Activating Token Index: 78