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

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

Neuron 2246 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0540. Min Act: -0.0002

Data Index: 355840 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0532. Min Act: -0.0003

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0524. Min Act: -0.0003

Data Index: 323646 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1058281 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0513. Min Act: -0.0003

Data Index: 678907 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0506. Min Act: -0.0003

Data Index: 237673 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0502. Min Act: -0.0002

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0499. Min Act: -0.0003

Data Index: 834122 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0494. Min Act: -0.0003

Data Index: 930454 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1058852 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1310434 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1289578 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0464. Min Act: -0.0002

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0470. Min Act: -0.0003

Data Index: 763220 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0464. Min Act: -0.0002

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0461. Min Act: -0.0003

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 673