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

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

Neuron 3196 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: 3.1231. Min Range: -3.1231

Max Act: 3.0166. Min Act: -0.0000

Data Index: 906789 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 3.1231. Min Range: -3.1231

Max Act: 3.1231. Min Act: -0.0000

Data Index: 982422 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.8033. Min Act: -0.0000

Data Index: 1244038 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.7419. Min Act: -0.0000

Data Index: 165699 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6990. Min Act: -0.0000

Data Index: 906715 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.8059. Min Act: -0.0000

Data Index: 408619 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.8542. Min Act: -0.0000

Data Index: 1296335 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.7271. Min Act: -0.0000

Data Index: 571713 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6778. Min Act: -0.0000

Data Index: 64509 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.5379. Min Act: -0.0000

Data Index: 758221 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6599. Min Act: -0.0000

Data Index: 660468 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6706. Min Act: -0.0000

Data Index: 261337 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.5448. Min Act: -0.0000

Data Index: 165738 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6633. Min Act: -0.0000

Data Index: 80205 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6447. Min Act: -0.0000

Data Index: 87312 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.6451. Min Act: -0.0000

Data Index: 310099 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.5281. Min Act: -0.0000

Data Index: 1326647 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.7839. Min Act: -0.0000

Data Index: 99055 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.7939. Min Act: -0.0000

Data Index: 353937 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 3.1231. Min Range: -3.1231

Max Act: 2.5013. Min Act: -0.0000

Data Index: 1224149 (C4 (Web Text))

Max Activating Token Index: 365