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

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

Neuron 2001 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: 0.0717. Min Range: -0.0717

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1339425 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0707. Min Act: -0.0003

Data Index: 207694 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0599. Min Act: -0.0003

Data Index: 603244 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0561. Min Act: -0.0003

Data Index: 759290 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0552. Min Act: -0.0003

Data Index: 393249 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0539. Min Act: -0.0003

Data Index: 54986 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0529. Min Act: -0.0003

Data Index: 28106 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0523. Min Act: -0.0003

Data Index: 638811 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0531. Min Act: -0.0004

Data Index: 1356162 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0511. Min Act: -0.0004

Data Index: 924180 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0510. Min Act: -0.0003

Data Index: 628735 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0482. Min Act: -0.0002

Data Index: 914074 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0482. Min Act: -0.0003

Data Index: 55374 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0443. Min Act: -0.0003

Data Index: 224892 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1336964 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0432. Min Act: -0.0003

Data Index: 696263 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0459. Min Act: -0.0003

Data Index: 527010 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0515. Min Act: -0.0003

Data Index: 197698 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0484. Min Act: -0.0003

Data Index: 78761 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0717. Min Range: -0.0717

Max Act: 0.0446. Min Act: -0.0003

Data Index: 208481 (C4 (Web Text))

Max Activating Token Index: 33