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

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

Neuron 256 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: 1.9220. Min Range: -1.9220

Max Act: 1.9220. Min Act: -0.0000

Data Index: 1308379 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.3578. Min Act: -0.0000

Data Index: 143707 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.2351. Min Act: -0.0000

Data Index: 14689 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1479. Min Act: -0.0000

Data Index: 822644 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0941. Min Act: -0.0000

Data Index: 478930 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1784. Min Act: -0.0000

Data Index: 785573 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1287143 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1714. Min Act: -0.0000

Data Index: 235099 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0720. Min Act: -0.0000

Data Index: 151151 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9484. Min Act: -0.0000

Data Index: 965961 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9764. Min Act: -0.0000

Data Index: 848159 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0131. Min Act: -0.0000

Data Index: 452606 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0869. Min Act: -0.0000

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1339250 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9244. Min Act: -0.0000

Data Index: 763603 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9131. Min Act: -0.0000

Data Index: 403076 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0226. Min Act: -0.0000

Data Index: 715744 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0315. Min Act: -0.0000

Data Index: 684025 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.9293. Min Act: -0.0000

Data Index: 644673 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.9220. Min Range: -1.9220

Max Act: 0.8785. Min Act: -0.0000

Data Index: 696254 (C4 (Web Text))

Max Activating Token Index: 170