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

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

Neuron 2005 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2724. Min Range: -4.2724

Max Act: 4.2724. Min Act: -0.0000

Data Index: 772158 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.2899. Min Act: -0.0000

Data Index: 670732 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.7482. Min Act: -0.0000

Data Index: 622249 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.6033. Min Act: -0.0000

Data Index: 268150 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.4017. Min Act: -0.0000

Data Index: 757451 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.2607. Min Act: -0.0000

Data Index: 456513 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.4914. Min Act: -0.0000

Data Index: 135106 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.2268. Min Act: -0.0000

Data Index: 243000 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.1722. Min Act: -0.0000

Data Index: 713961 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.1768. Min Act: -0.0000

Data Index: 608620 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 4.2724. Min Range: -4.2724

Max Act: 2.7541. Min Act: -0.0000

Data Index: 517973 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.0729. Min Act: -0.0000

Data Index: 944143 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 4.2724. Min Range: -4.2724

Max Act: 2.4525. Min Act: -0.0000

Data Index: 135053 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 4.2724. Min Range: -4.2724

Max Act: 2.6895. Min Act: -0.0000

Data Index: 434026 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.0213. Min Act: -0.0000

Data Index: 421809 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.1348. Min Act: -0.0000

Data Index: 238314 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.2794. Min Act: -0.0000

Data Index: 131020 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.2278. Min Act: -0.0000

Data Index: 1335678 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 4.2724. Min Range: -4.2724

Max Act: 2.9346. Min Act: -0.0000

Data Index: 1016231 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 4.2724. Min Range: -4.2724

Max Act: 3.0598. Min Act: -0.0000

Data Index: 589608 (C4 (Web Text))

Max Activating Token Index: 26