Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1028 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1541395 (Python Code)

Max Activating Token Index: 283

Text #1

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0564. Min Act: -0.0003

Data Index: 77480 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1424429 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0473. Min Act: -0.0003

Data Index: 717274 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1363125 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0482. Min Act: -0.0003

Data Index: 1585949 (Python Code)

Max Activating Token Index: 911

Text #6

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0502. Min Act: -0.0003

Data Index: 786085 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0481. Min Act: -0.0003

Data Index: 260899 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0507. Min Act: -0.0003

Data Index: 347964 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1280914 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1512069 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0474. Min Act: -0.0003

Data Index: 110288 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0490. Min Act: -0.0004

Data Index: 28543 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1555179 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1041756 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0456. Min Act: -0.0003

Data Index: 913623 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1234620 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1469586 (Python Code)

Max Activating Token Index: 952

Text #18

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1240847 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.0607. Min Range: -0.0607

Max Act: 0.0444. Min Act: -0.0003

Data Index: 176006 (C4 (Web Text))

Max Activating Token Index: 587