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

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

Neuron 2796 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: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1026117 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0459. Min Act: -0.0002

Data Index: 568368 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1146135 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0424. Min Act: -0.0002

Data Index: 852229 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0411. Min Act: -0.0002

Data Index: 524880 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1108135 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0423. Min Act: -0.0002

Data Index: 780368 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0416. Min Act: -0.0001

Data Index: 303301 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0384. Min Act: -0.0002

Data Index: 411171 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0396. Min Act: -0.0002

Data Index: 371975 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1001815 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0389. Min Act: -0.0002

Data Index: 126045 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0402. Min Act: -0.0001

Data Index: 722148 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0419. Min Act: -0.0001

Data Index: 887092 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0432. Min Act: -0.0001

Data Index: 547458 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0382. Min Act: -0.0002

Data Index: 503799 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0381. Min Act: -0.0002

Data Index: 389050 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0411. Min Act: -0.0002

Data Index: 639558 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0411. Min Act: -0.0001

Data Index: 554904 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0392. Min Act: -0.0002

Data Index: 442298 (C4 (Web Text))

Max Activating Token Index: 976