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

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

Neuron 4737 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1355. Min Range: -2.1355

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1120110 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 2.1355. Min Range: -2.1355

Max Act: 2.1355. Min Act: -0.0000

Data Index: 657365 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.7871. Min Act: -0.0000

Data Index: 1626124 (Python Code)

Max Activating Token Index: 788

Text #3

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5975. Min Act: -0.0000

Data Index: 420778 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.7741. Min Act: -0.0000

Data Index: 31845 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1166883 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5128. Min Act: -0.0000

Data Index: 1125857 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5876. Min Act: -0.0000

Data Index: 692209 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5779. Min Act: -0.0000

Data Index: 914171 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5705. Min Act: -0.0000

Data Index: 330506 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1140042 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.5291. Min Act: -0.0000

Data Index: 755063 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4371. Min Act: -0.0000

Data Index: 497635 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1347657 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1071237 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4580. Min Act: -0.0000

Data Index: 231883 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.3859. Min Act: -0.0000

Data Index: 738286 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1352680 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4537. Min Act: -0.0000

Data Index: 360198 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 2.1355. Min Range: -2.1355

Max Act: 1.4331. Min Act: -0.0000

Data Index: 416870 (C4 (Web Text))

Max Activating Token Index: 913