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

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

Neuron 161 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0003

Data Index: 801988 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1283160 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0574. Min Act: -0.0003

Data Index: 438221 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0522. Min Act: -0.0003

Data Index: 773239 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0523. Min Act: -0.0003

Data Index: 17734 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0523. Min Act: -0.0003

Data Index: 126017 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1296398 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0478. Min Act: -0.0002

Data Index: 963496 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0492. Min Act: -0.0002

Data Index: 479647 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0473. Min Act: -0.0002

Data Index: 429945 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0495. Min Act: -0.0003

Data Index: 77219 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0464. Min Act: -0.0002

Data Index: 796179 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0447. Min Act: -0.0002

Data Index: 497825 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0479. Min Act: -0.0002

Data Index: 873902 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0468. Min Act: -0.0003

Data Index: 598480 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0468. Min Act: -0.0002

Data Index: 916452 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0457. Min Act: -0.0003

Data Index: 473948 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1138192 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0463. Min Act: -0.0002

Data Index: 281414 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0452. Min Act: -0.0003

Data Index: 298165 (C4 (Web Text))

Max Activating Token Index: 535