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

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

Neuron 4609 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.9982. Min Act: -0.0000

Data Index: 950129 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.9842. Min Act: -0.0000

Data Index: 736314 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.9300. Min Act: -0.0000

Data Index: 674264 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.7891. Min Act: -0.0000

Data Index: 109355 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.8545. Min Act: -0.0000

Data Index: 1047594 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.8393. Min Act: -0.0000

Data Index: 245126 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.7945. Min Act: -0.0000

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6208. Min Act: -0.0000

Data Index: 9318 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1343451 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.8015. Min Act: -0.0000

Data Index: 805300 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1200813 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6974. Min Act: -0.0000

Data Index: 790815 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6902. Min Act: -0.0000

Data Index: 352963 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6403. Min Act: -0.0000

Data Index: 975870 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1052590 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6364. Min Act: -0.0000

Data Index: 540750 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.6182. Min Act: -0.0000

Data Index: 1221371 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3986. Min Act: -0.0000

Data Index: 328349 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.3358. Min Act: -0.0000

Data Index: 224265 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 1.9982. Min Range: -1.9982

Max Act: 1.4077. Min Act: -0.0000

Data Index: 669320 (C4 (Web Text))

Max Activating Token Index: 229