Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4857. Min Act: -0.0000

Data Index: 528210 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4269. Min Act: -0.0000

Data Index: 427411 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4221. Min Act: -0.0000

Data Index: 606439 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4185. Min Act: -0.0000

Data Index: 778424 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.4040. Min Act: -0.0000

Data Index: 43128 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3837. Min Act: -0.0000

Data Index: 552752 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3788. Min Act: -0.0000

Data Index: 330524 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3620. Min Act: -0.0000

Data Index: 996973 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3728. Min Act: -0.0000

Data Index: 696636 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1240533 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1066639 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3630. Min Act: -0.0000

Data Index: 709799 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3602. Min Act: -0.0000

Data Index: 416221 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3569. Min Act: -0.0000

Data Index: 193638 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3663. Min Act: -0.0000

Data Index: 232731 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3334. Min Act: -0.0000

Data Index: 661828 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3321. Min Act: -0.0000

Data Index: 599735 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3376. Min Act: -0.0000

Data Index: 249939 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3273. Min Act: -0.0000

Data Index: 653267 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.4857. Min Range: -0.4857

Max Act: 0.3258. Min Act: -0.0000

Data Index: 716250 (C4 (Web Text))

Max Activating Token Index: 380