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

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

Neuron 2338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.9613. Min Act: -0.0000

Data Index: 830491 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8391. Min Act: -0.0000

Data Index: 208791 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8073. Min Act: -0.0000

Data Index: 890112 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8242. Min Act: -0.0000

Data Index: 463969 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8119. Min Act: -0.0000

Data Index: 508553 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7694. Min Act: -0.0000

Data Index: 278464 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7914. Min Act: -0.0000

Data Index: 318532 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1286302 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7432. Min Act: -0.0000

Data Index: 617701 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7771. Min Act: -0.0000

Data Index: 858534 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7574. Min Act: -0.0000

Data Index: 25085 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7554. Min Act: 0.0000

Data Index: 707902 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7505. Min Act: -0.0000

Data Index: 882008 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7306. Min Act: -0.0000

Data Index: 847011 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7469. Min Act: -0.0000

Data Index: 311763 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7004. Min Act: 0.0000

Data Index: 501038 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7097. Min Act: -0.0000

Data Index: 577072 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7325. Min Act: -0.0000

Data Index: 130839 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.9613. Min Range: -0.9613

Max Act: 0.7049. Min Act: -0.0000

Data Index: 72398 (C4 (Web Text))

Max Activating Token Index: 954