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

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

Neuron 546 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: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0006

Data Index: 473185 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0548. Min Act: -0.0006

Data Index: 212106 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0540. Min Act: -0.0006

Data Index: 945926 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1030167 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0525. Min Act: -0.0006

Data Index: 1060144 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0505. Min Act: -0.0006

Data Index: 675931 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0535. Min Act: -0.0006

Data Index: 1349788 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0498. Min Act: -0.0006

Data Index: 1277987 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0498. Min Act: -0.0006

Data Index: 33257 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0497. Min Act: -0.0006

Data Index: 68759 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0497. Min Act: -0.0006

Data Index: 972204 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0526. Min Act: -0.0006

Data Index: 1176021 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0503. Min Act: -0.0006

Data Index: 832377 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0513. Min Act: -0.0006

Data Index: 184136 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0502. Min Act: -0.0006

Data Index: 255444 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0483. Min Act: -0.0006

Data Index: 776687 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0483. Min Act: -0.0006

Data Index: 369429 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0461. Min Act: -0.0006

Data Index: 1187951 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1220332 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0487. Min Act: -0.0006

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 993