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

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

Neuron 3082 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: 0.7568. Min Range: -0.7568

Max Act: 0.7568. Min Act: -0.0001

Data Index: 498847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.7503. Min Act: -0.0001

Data Index: 708963 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.7377. Min Act: -0.0001

Data Index: 1139858 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1042261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6644. Min Act: -0.0001

Data Index: 529277 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6823. Min Act: -0.0001

Data Index: 673415 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6225. Min Act: -0.0002

Data Index: 702649 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5754. Min Act: -0.0001

Data Index: 890392 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6388. Min Act: -0.0001

Data Index: 387437 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5933. Min Act: -0.0002

Data Index: 6233 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6507. Min Act: -0.0002

Data Index: 1170191 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5619. Min Act: -0.0001

Data Index: 81424 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5293. Min Act: -0.0001

Data Index: 837762 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5804. Min Act: -0.0001

Data Index: 520646 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5540. Min Act: -0.0002

Data Index: 764845 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5143. Min Act: -0.0001

Data Index: 1299768 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5653. Min Act: -0.0001

Data Index: 1051968 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5363. Min Act: -0.0001

Data Index: 530624 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.6093. Min Act: -0.0001

Data Index: 1234364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.7568. Min Range: -0.7568

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1308585 (C4 (Web Text))

Max Activating Token Index: 1023