Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0499. Min Act: -0.0005

Data Index: 508893 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0519. Min Act: -0.0005

Data Index: 1095651 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0005

Data Index: 1245600 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0516. Min Act: -0.0005

Data Index: 907620 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0512. Min Act: -0.0005

Data Index: 1190543 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0502. Min Act: -0.0005

Data Index: 973581 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0479. Min Act: -0.0005

Data Index: 632222 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0487. Min Act: -0.0005

Data Index: 1201200 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0468. Min Act: -0.0005

Data Index: 704307 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0494. Min Act: -0.0005

Data Index: 654005 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0481. Min Act: -0.0005

Data Index: 941482 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0475. Min Act: -0.0005

Data Index: 1243624 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0448. Min Act: -0.0005

Data Index: 410405 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0458. Min Act: -0.0005

Data Index: 1331752 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0419. Min Act: -0.0005

Data Index: 389756 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0446. Min Act: -0.0004

Data Index: 102141 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0453. Min Act: -0.0005

Data Index: 264193 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0460. Min Act: -0.0005

Data Index: 1128451 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0460. Min Act: -0.0005

Data Index: 682579 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0452. Min Act: -0.0005

Data Index: 1525968 (Python Code)

Max Activating Token Index: 361