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

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

Neuron 5954 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0489. Min Range: -5.0489

Max Act: 5.0489. Min Act: -0.0000

Data Index: 1140567 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 5.0489. Min Range: -5.0489

Max Act: 4.0822. Min Act: -0.0001

Data Index: 962734 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 5.0489. Min Range: -5.0489

Max Act: 4.3046. Min Act: -0.0001

Data Index: 1146313 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 5.0489. Min Range: -5.0489

Max Act: 4.0262. Min Act: -0.0000

Data Index: 265700 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 5.0489. Min Range: -5.0489

Max Act: 4.2781. Min Act: -0.0001

Data Index: 765007 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.7400. Min Act: -0.0000

Data Index: 441328 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.2898. Min Act: -0.0000

Data Index: 729434 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.5899. Min Act: -0.0000

Data Index: 905948 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.3889. Min Act: -0.0000

Data Index: 568399 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.6441. Min Act: -0.0001

Data Index: 330789 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.4651. Min Act: -0.0001

Data Index: 1137399 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.5913. Min Act: -0.0001

Data Index: 1193199 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.4217. Min Act: -0.0001

Data Index: 754426 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.5396. Min Act: -0.0000

Data Index: 207019 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.6708. Min Act: -0.0001

Data Index: 1320770 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.5088. Min Act: -0.0000

Data Index: 55838 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.1790. Min Act: -0.0000

Data Index: 1231590 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.6950. Min Act: -0.0001

Data Index: 954368 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.2126. Min Act: -0.0001

Data Index: 1111747 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 5.0489. Min Range: -5.0489

Max Act: 3.5347. Min Act: -0.0001

Data Index: 506142 (C4 (Web Text))

Max Activating Token Index: 644