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

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

Neuron 696 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.7190. Min Act: -0.0000

Data Index: 241208 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6291. Min Act: -0.0000

Data Index: 840909 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1203057 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1213944 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.6187. Min Act: -0.0000

Data Index: 681639 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5420. Min Act: -0.0000

Data Index: 471470 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5207. Min Act: -0.0000

Data Index: 660698 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1064326 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5243. Min Act: -0.0000

Data Index: 998076 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1114312 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5150. Min Act: -0.0000

Data Index: 993401 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5113. Min Act: -0.0000

Data Index: 712489 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5240. Min Act: -0.0000

Data Index: 177007 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5612. Min Act: -0.0001

Data Index: 1092542 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.5021. Min Act: -0.0000

Data Index: 956660 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4864. Min Act: -0.0000

Data Index: 657890 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4603. Min Act: -0.0000

Data Index: 478841 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1018402 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1316396 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.7190. Min Range: -0.7190

Max Act: 0.4766. Min Act: -0.0000

Data Index: 842729 (C4 (Web Text))

Max Activating Token Index: 365