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

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

Neuron 3348 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: 0.5072. Min Range: -0.5072

Max Act: 0.5072. Min Act: -0.0001

Data Index: 99770 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4351. Min Act: -0.0000

Data Index: 635544 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3714. Min Act: -0.0000

Data Index: 439562 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3679. Min Act: -0.0001

Data Index: 172111 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1295008 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3670. Min Act: -0.0001

Data Index: 1581170 (Python Code)

Max Activating Token Index: 84

Text #6

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3484. Min Act: -0.0001

Data Index: 543653 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3334. Min Act: -0.0000

Data Index: 14569 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3315. Min Act: -0.0000

Data Index: 423669 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3444. Min Act: -0.0000

Data Index: 6936 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3353. Min Act: -0.0000

Data Index: 648414 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3455. Min Act: -0.0000

Data Index: 643544 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3344. Min Act: -0.0000

Data Index: 656244 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1238417 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1413202 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3279. Min Act: -0.0000

Data Index: 417696 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3246. Min Act: -0.0000

Data Index: 633572 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3103. Min Act: -0.0000

Data Index: 813079 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1261720 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3058. Min Act: -0.0001

Data Index: 1303323 (C4 (Web Text))

Max Activating Token Index: 354