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

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

Neuron 3932 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4999. Min Act: -0.0000

Data Index: 119004 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.5033. Min Act: -0.0000

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1273852 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4552. Min Act: -0.0000

Data Index: 461702 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1209591 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4464. Min Act: -0.0000

Data Index: 373777 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4413. Min Act: -0.0000

Data Index: 952911 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4263. Min Act: -0.0000

Data Index: 596724 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4263. Min Act: 0.0000

Data Index: 1317852 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4151. Min Act: -0.0000

Data Index: 900050 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4038. Min Act: 0.0000

Data Index: 1083017 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4093. Min Act: -0.0000

Data Index: 332392 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.4447. Min Act: -0.0000

Data Index: 324941 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3970. Min Act: -0.0000

Data Index: 1147788 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3979. Min Act: -0.0000

Data Index: 695669 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3845. Min Act: -0.0000

Data Index: 876810 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1168755 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1048190 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3848. Min Act: -0.0000

Data Index: 450086 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.5075. Min Range: -0.5075

Max Act: 0.3821. Min Act: 0.0001

Data Index: 918031 (C4 (Web Text))

Max Activating Token Index: 1015