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

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

Neuron 2583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.2956. Min Act: -0.0000

Data Index: 422613 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1159938 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1127694 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.0736. Min Act: -0.0000

Data Index: 202142 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1209002 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9704. Min Act: -0.0000

Data Index: 272002 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9924. Min Act: -0.0000

Data Index: 16942 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9508. Min Act: -0.0000

Data Index: 703323 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9837. Min Act: -0.0000

Data Index: 925833 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9486. Min Act: -0.0000

Data Index: 376928 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1587800 (Python Code)

Max Activating Token Index: 858

Text #11

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1126113 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9225. Min Act: -0.0000

Data Index: 563838 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9131. Min Act: -0.0000

Data Index: 40749 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9013. Min Act: -0.0000

Data Index: 250223 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1111828 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9551. Min Act: -0.0000

Data Index: 326668 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1322362 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9106. Min Act: -0.0000

Data Index: 792858 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1190090 (C4 (Web Text))

Max Activating Token Index: 333