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

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

Neuron 2056 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: 0.5220. Min Range: -0.5220

Max Act: 0.5220. Min Act: -0.0000

Data Index: 264923 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3927. Min Act: -0.0000

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3018. Min Act: -0.0000

Data Index: 801016 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3464. Min Act: -0.0000

Data Index: 536068 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3411. Min Act: -0.0000

Data Index: 551494 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1161574 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3121. Min Act: -0.0000

Data Index: 597878 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1348461 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1064342 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1281533 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2948. Min Act: -0.0000

Data Index: 563396 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1318141 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3151. Min Act: -0.0000

Data Index: 389113 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3021. Min Act: -0.0000

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1384388 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1505480 (Python Code)

Max Activating Token Index: 371

Text #17

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.3090. Min Act: -0.0000

Data Index: 708064 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2968. Min Act: -0.0000

Data Index: 482208 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.5220. Min Range: -0.5220

Max Act: 0.2852. Min Act: -0.0000

Data Index: 637526 (C4 (Web Text))

Max Activating Token Index: 247