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

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

Neuron 5652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.3382. Min Act: -0.0000

Data Index: 109117 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.0818. Min Act: -0.0000

Data Index: 1024675 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.1309. Min Act: -0.0000

Data Index: 71556 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.1036. Min Act: -0.0000

Data Index: 1019476 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 2.3382. Min Range: -2.3382

Max Act: 2.0158. Min Act: -0.0000

Data Index: 1046407 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9827. Min Act: -0.0000

Data Index: 680518 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9780. Min Act: -0.0000

Data Index: 932730 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8552. Min Act: -0.0000

Data Index: 265885 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9589. Min Act: -0.0000

Data Index: 378019 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9468. Min Act: -0.0000

Data Index: 1194825 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.9317. Min Act: -0.0000

Data Index: 222100 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8088. Min Act: -0.0000

Data Index: 349272 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8495. Min Act: -0.0000

Data Index: 688824 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7131. Min Act: -0.0000

Data Index: 422667 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1187481 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1326498 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7779. Min Act: -0.0000

Data Index: 849284 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.7687. Min Act: -0.0000

Data Index: 897379 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.8709. Min Act: -0.0000

Data Index: 671123 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 2.3382. Min Range: -2.3382

Max Act: 1.6217. Min Act: -0.0000

Data Index: 760090 (C4 (Web Text))

Max Activating Token Index: 265