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

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

Neuron 1594 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: 0.0536. Min Range: -0.0536

Max Act: 0.0532. Min Act: -0.0005

Data Index: 1041654 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0005

Data Index: 803929 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0504. Min Act: -0.0005

Data Index: 408052 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1148239 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0509. Min Act: -0.0005

Data Index: 184169 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0471. Min Act: -0.0005

Data Index: 481600 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0503. Min Act: -0.0005

Data Index: 219230 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0473. Min Act: -0.0005

Data Index: 787508 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0477. Min Act: -0.0005

Data Index: 565452 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0495. Min Act: -0.0005

Data Index: 1007573 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0477. Min Act: -0.0005

Data Index: 982845 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0476. Min Act: -0.0005

Data Index: 228108 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1260741 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0461. Min Act: -0.0005

Data Index: 953250 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0472. Min Act: -0.0005

Data Index: 302376 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0461. Min Act: -0.0005

Data Index: 892733 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0434. Min Act: -0.0005

Data Index: 229368 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0433. Min Act: -0.0005

Data Index: 544332 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0422. Min Act: -0.0005

Data Index: 260476 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0446. Min Act: -0.0005

Data Index: 729632 (C4 (Web Text))

Max Activating Token Index: 456