Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.1073. Min Range: -4.1073

Max Act: 4.1073. Min Act: -0.0002

Data Index: 1334696 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.7970. Min Act: -0.0002

Data Index: 1022557 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 4.1073. Min Range: -4.1073

Max Act: 4.0936. Min Act: -0.0002

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.6171. Min Act: -0.0002

Data Index: 1282979 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.1770. Min Act: -0.0002

Data Index: 667321 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.4286. Min Act: -0.0002

Data Index: 262334 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.6002. Min Act: -0.0002

Data Index: 306416 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.3745. Min Act: -0.0002

Data Index: 76399 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.4861. Min Act: -0.0002

Data Index: 1164830 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.9516. Min Act: -0.0002

Data Index: 1353840 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.5787. Min Act: -0.0002

Data Index: 1153779 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.8005. Min Act: -0.0002

Data Index: 1303611 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.6801. Min Act: -0.0002

Data Index: 1014685 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.0574. Min Act: -0.0002

Data Index: 132129 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.4218. Min Act: -0.0002

Data Index: 351727 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.0528. Min Act: -0.0002

Data Index: 759826 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 4.1073. Min Range: -4.1073

Max Act: 3.1318. Min Act: -0.0002

Data Index: 779858 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.7371. Min Act: -0.0002

Data Index: 286241 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.9801. Min Act: -0.0002

Data Index: 79754 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 4.1073. Min Range: -4.1073

Max Act: 2.1327. Min Act: -0.0002

Data Index: 183470 (C4 (Web Text))

Max Activating Token Index: 251