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

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

Neuron 3427 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3750. Min Range: -5.3750

Max Act: 5.3750. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.4856. Min Act: -0.0000

Data Index: 571912 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.5994. Min Act: 0.0000

Data Index: 955370 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.7105. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.4295. Min Act: -0.0000

Data Index: 154015 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.3042. Min Act: -0.0000

Data Index: 1294217 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.1037. Min Act: -0.0000

Data Index: 136324 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.4111. Min Act: 0.0000

Data Index: 1210520 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.1820. Min Act: -0.0000

Data Index: 901491 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9548. Min Act: -0.0000

Data Index: 1056411 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9472. Min Act: -0.0000

Data Index: 83657 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.0671. Min Act: -0.0000

Data Index: 1172029 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.0748. Min Act: -0.0000

Data Index: 312516 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 5.3750. Min Range: -5.3750

Max Act: 3.0601. Min Act: -0.0000

Data Index: 216669 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9998. Min Act: -0.0000

Data Index: 26563 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.8082. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9617. Min Act: -0.0000

Data Index: 592085 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9380. Min Act: -0.0000

Data Index: 555734 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9248. Min Act: -0.0000

Data Index: 257430 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 5.3750. Min Range: -5.3750

Max Act: 2.9040. Min Act: -0.0000

Data Index: 826985 (C4 (Web Text))

Max Activating Token Index: 611