Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0006

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0553. Min Act: -0.0006

Data Index: 480033 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0554. Min Act: -0.0006

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0540. Min Act: -0.0006

Data Index: 1284253 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0514. Min Act: -0.0006

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0517. Min Act: -0.0006

Data Index: 227518 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0485. Min Act: -0.0006

Data Index: 197999 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0518. Min Act: -0.0006

Data Index: 1044970 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0506. Min Act: -0.0006

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0525. Min Act: -0.0006

Data Index: 25521 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0507. Min Act: -0.0006

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0484. Min Act: -0.0006

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0508. Min Act: -0.0006

Data Index: 816522 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0466. Min Act: -0.0006

Data Index: 502679 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0491. Min Act: -0.0006

Data Index: 148324 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0505. Min Act: -0.0006

Data Index: 190431 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0486. Min Act: -0.0006

Data Index: 32515 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0475. Min Act: -0.0006

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0474. Min Act: -0.0006

Data Index: 458796 (C4 (Web Text))

Max Activating Token Index: 895