Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.8078. Min Act: -0.0000

Data Index: 200357 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7621. Min Act: -0.0000

Data Index: 938927 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1297740 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7315. Min Act: -0.0000

Data Index: 53622 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6623. Min Act: -0.0000

Data Index: 372806 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1081498 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6937. Min Act: -0.0000

Data Index: 852263 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1447238 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6666. Min Act: -0.0000

Data Index: 338869 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1170903 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1237124 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6369. Min Act: -0.0000

Data Index: 832652 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6467. Min Act: -0.0000

Data Index: 749458 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6498. Min Act: -0.0000

Data Index: 404127 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6158. Min Act: -0.0000

Data Index: 77267 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6064. Min Act: -0.0000

Data Index: 107602 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6064. Min Act: -0.0000

Data Index: 141389 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1256754 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6000. Min Act: -0.0000

Data Index: 27579 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1041305 (C4 (Web Text))

Max Activating Token Index: 977