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

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

Neuron 1273 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: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0006

Data Index: 1243591 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0533. Min Act: -0.0006

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0524. Min Act: -0.0006

Data Index: 1011358 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0509. Min Act: -0.0006

Data Index: 163332 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0518. Min Act: -0.0006

Data Index: 808572 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0526. Min Act: -0.0006

Data Index: 959058 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1281476 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1140039 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0512. Min Act: -0.0006

Data Index: 608448 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1321243 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0501. Min Act: -0.0006

Data Index: 523689 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1258620 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0486. Min Act: -0.0006

Data Index: 82894 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0434. Min Act: -0.0006

Data Index: 472804 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0471. Min Act: -0.0006

Data Index: 1227893 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0477. Min Act: -0.0006

Data Index: 247035 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0477. Min Act: -0.0006

Data Index: 82466 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0483. Min Act: -0.0005

Data Index: 15588 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0473. Min Act: -0.0006

Data Index: 897895 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0492. Min Act: -0.0006

Data Index: 662492 (C4 (Web Text))

Max Activating Token Index: 986