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

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

Neuron 3639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0002

Data Index: 121780 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0493. Min Act: -0.0002

Data Index: 33750 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0463. Min Act: -0.0002

Data Index: 119956 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1075174 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0428. Min Act: -0.0002

Data Index: 300320 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1095370 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0444. Min Act: -0.0002

Data Index: 301589 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0418. Min Act: -0.0002

Data Index: 182375 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0428. Min Act: -0.0002

Data Index: 239033 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0431. Min Act: -0.0002

Data Index: 235397 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0424. Min Act: -0.0002

Data Index: 272418 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0400. Min Act: -0.0002

Data Index: 918142 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0406. Min Act: -0.0002

Data Index: 200050 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0389. Min Act: -0.0002

Data Index: 893913 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1112765 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1109672 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1011666 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1359181 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0377. Min Act: -0.0002

Data Index: 735949 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1069128 (C4 (Web Text))

Max Activating Token Index: 716