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

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

Neuron 1543 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: 0.0604. Min Range: -0.0604

Max Act: 0.0594. Min Act: -0.0003

Data Index: 742940 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1002945 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0559. Min Act: -0.0003

Data Index: 733295 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1566432 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0544. Min Act: -0.0004

Data Index: 919442 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1294552 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0524. Min Act: -0.0003

Data Index: 142058 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1651696 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1357014 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1380110 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0527. Min Act: -0.0003

Data Index: 493763 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1493285 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1162899 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1289532 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0518. Min Act: -0.0003

Data Index: 387815 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1173731 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0499. Min Act: -0.0003

Data Index: 191762 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1571568 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1084587 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0493. Min Act: -0.0003

Data Index: 900097 (C4 (Web Text))

Max Activating Token Index: 418