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

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

Neuron 148 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4758. Min Range: -3.4758

Max Act: 3.4758. Min Act: -0.0000

Data Index: 1283429 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.6874. Min Act: -0.0000

Data Index: 1225463 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.8132. Min Act: -0.0000

Data Index: 360730 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.7841. Min Act: -0.0000

Data Index: 1339266 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.6060. Min Act: -0.0000

Data Index: 529276 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.5470. Min Act: -0.0000

Data Index: 630867 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.6701. Min Act: -0.0000

Data Index: 801658 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.5363. Min Act: -0.0000

Data Index: 1276304 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.5104. Min Act: -0.0000

Data Index: 1109051 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.3334. Min Act: -0.0001

Data Index: 979594 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.4279. Min Act: -0.0000

Data Index: 1035830 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.6834. Min Act: -0.0000

Data Index: 903967 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.4004. Min Act: -0.0000

Data Index: 1165454 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.5217. Min Act: -0.0000

Data Index: 338284 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.4805. Min Act: -0.0000

Data Index: 683367 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.3052. Min Act: -0.0000

Data Index: 1051949 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.2642. Min Act: -0.0000

Data Index: 424114 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.1411. Min Act: -0.0000

Data Index: 445421 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1004932 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.4758. Min Range: -3.4758

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1171572 (C4 (Web Text))

Max Activating Token Index: 787