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

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

Neuron 405 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: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0006

Data Index: 952436 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0634. Min Act: -0.0006

Data Index: 144161 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0565. Min Act: -0.0006

Data Index: 630481 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0554. Min Act: -0.0006

Data Index: 176389 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0531. Min Act: -0.0006

Data Index: 580983 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0528. Min Act: -0.0006

Data Index: 912826 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0523. Min Act: -0.0006

Data Index: 805477 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0526. Min Act: -0.0006

Data Index: 597639 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0498. Min Act: -0.0006

Data Index: 19213 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0498. Min Act: -0.0006

Data Index: 667054 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0466. Min Act: -0.0006

Data Index: 217466 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1106809 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0486. Min Act: -0.0006

Data Index: 347026 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0486. Min Act: -0.0006

Data Index: 870322 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0476. Min Act: -0.0006

Data Index: 1190899 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0496. Min Act: -0.0006

Data Index: 659820 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0483. Min Act: -0.0006

Data Index: 569384 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0464. Min Act: -0.0006

Data Index: 1144576 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0494. Min Act: -0.0006

Data Index: 296284 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0482. Min Act: -0.0006

Data Index: 1176020 (C4 (Web Text))

Max Activating Token Index: 729