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

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

Neuron 2805 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: 1.4253. Min Range: -1.4253

Max Act: 1.4253. Min Act: -0.0001

Data Index: 933485 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.2838. Min Act: -0.0000

Data Index: 630575 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.2447. Min Act: -0.0000

Data Index: 636239 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.2404. Min Act: -0.0000

Data Index: 761012 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.1497. Min Act: -0.0000

Data Index: 998936 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.1516. Min Act: -0.0000

Data Index: 747348 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1081338 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.1039. Min Act: -0.0000

Data Index: 468501 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0638. Min Act: -0.0000

Data Index: 676769 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1208531 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0870. Min Act: -0.0000

Data Index: 882220 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0579. Min Act: -0.0001

Data Index: 526898 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0457. Min Act: -0.0000

Data Index: 519720 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0354. Min Act: -0.0001

Data Index: 725578 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0386. Min Act: -0.0000

Data Index: 570417 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.4253. Min Range: -1.4253

Max Act: 0.9858. Min Act: -0.0001

Data Index: 309121 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.4253. Min Range: -1.4253

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1261870 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 1.4253. Min Range: -1.4253

Max Act: 0.9743. Min Act: -0.0000

Data Index: 697474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.4253. Min Range: -1.4253

Max Act: 0.9729. Min Act: -0.0001

Data Index: 522736 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.4253. Min Range: -1.4253

Max Act: 0.9877. Min Act: -0.0000

Data Index: 301968 (C4 (Web Text))

Max Activating Token Index: 130