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

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

Neuron 129 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: 0.0531. Min Range: -0.0531

Max Act: 0.0531. Min Act: -0.0006

Data Index: 576566 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0495. Min Act: -0.0006

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0514. Min Act: -0.0006

Data Index: 501061 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0464. Min Act: -0.0006

Data Index: 703560 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0450. Min Act: -0.0006

Data Index: 529081 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0483. Min Act: -0.0006

Data Index: 420833 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0461. Min Act: -0.0006

Data Index: 650873 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0452. Min Act: -0.0006

Data Index: 818972 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0443. Min Act: -0.0006

Data Index: 511268 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1069509 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0430. Min Act: -0.0006

Data Index: 1142094 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0428. Min Act: -0.0006

Data Index: 497877 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0434. Min Act: -0.0006

Data Index: 931078 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0423. Min Act: -0.0006

Data Index: 873497 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0423. Min Act: -0.0006

Data Index: 136632 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0430. Min Act: -0.0006

Data Index: 51136 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0439. Min Act: -0.0006

Data Index: 1346750 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0419. Min Act: -0.0005

Data Index: 851509 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0423. Min Act: -0.0005

Data Index: 1043250 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.0531. Min Range: -0.0531

Max Act: 0.0441. Min Act: -0.0006

Data Index: 975819 (C4 (Web Text))

Max Activating Token Index: 398