Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0607. Min Act: -0.0002

Data Index: 541206 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0610. Min Act: -0.0001

Data Index: 76762 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0577. Min Act: -0.0001

Data Index: 245800 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0579. Min Act: -0.0001

Data Index: 443797 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0519. Min Act: -0.0001

Data Index: 757897 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1053924 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1148262 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0499. Min Act: -0.0001

Data Index: 609526 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1089886 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0504. Min Act: -0.0002

Data Index: 699203 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0458. Min Act: -0.0001

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0512. Min Act: -0.0001

Data Index: 596266 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0526. Min Act: -0.0001

Data Index: 612371 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0499. Min Act: -0.0001

Data Index: 941535 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1248902 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0496. Min Act: -0.0001

Data Index: 33637 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0485. Min Act: -0.0001

Data Index: 382220 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0474. Min Act: -0.0001

Data Index: 556450 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1097267 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0610. Min Range: -0.0610

Max Act: 0.0489. Min Act: -0.0001

Data Index: 232357 (C4 (Web Text))

Max Activating Token Index: 372