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

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

Neuron 21 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: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1201442 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3631. Min Act: -0.0000

Data Index: 605544 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3282. Min Act: -0.0000

Data Index: 660927 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3056. Min Act: -0.0000

Data Index: 120412 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3205. Min Act: -0.0000

Data Index: 613806 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1194045 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1540236 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2614. Min Act: -0.0000

Data Index: 809373 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2597. Min Act: -0.0000

Data Index: 614366 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1254452 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2573. Min Act: -0.0000

Data Index: 528280 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2565. Min Act: -0.0000

Data Index: 427480 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2192. Min Act: -0.0000

Data Index: 425187 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2299. Min Act: -0.0000

Data Index: 947948 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1258701 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1004602 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2078. Min Act: -0.0000

Data Index: 944132 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2029. Min Act: -0.0000

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2144. Min Act: -0.0000

Data Index: 247320 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2036. Min Act: -0.0000

Data Index: 185104 (C4 (Web Text))

Max Activating Token Index: 339