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

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

Neuron 1381 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: 0.0577. Min Range: -0.0577

Max Act: 0.0577. Min Act: -0.0004

Data Index: 590033 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0533. Min Act: -0.0004

Data Index: 1203530 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0509. Min Act: -0.0003

Data Index: 318368 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0508. Min Act: -0.0003

Data Index: 624822 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0500. Min Act: -0.0004

Data Index: 689175 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0481. Min Act: -0.0004

Data Index: 371416 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0476. Min Act: -0.0004

Data Index: 1275314 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0471. Min Act: -0.0003

Data Index: 702241 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0465. Min Act: -0.0003

Data Index: 643845 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0470. Min Act: -0.0003

Data Index: 655185 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0470. Min Act: -0.0002

Data Index: 596733 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0473. Min Act: -0.0003

Data Index: 209153 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0448. Min Act: -0.0003

Data Index: 826146 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1046454 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0457. Min Act: -0.0003

Data Index: 94566 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0436. Min Act: -0.0003

Data Index: 703184 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0446. Min Act: -0.0003

Data Index: 535512 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0454. Min Act: -0.0003

Data Index: 944031 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0460. Min Act: -0.0003

Data Index: 252153 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0577. Min Range: -0.0577

Max Act: 0.0456. Min Act: -0.0003

Data Index: 7820 (C4 (Web Text))

Max Activating Token Index: 344