Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.9137. Min Act: -0.0001

Data Index: 1273948 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7704. Min Act: -0.0001

Data Index: 423886 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7204. Min Act: -0.0001

Data Index: 578602 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1048121 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1307568 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8039. Min Act: -0.0001

Data Index: 537128 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7306. Min Act: -0.0001

Data Index: 347430 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6925. Min Act: -0.0001

Data Index: 302152 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7650. Min Act: -0.0001

Data Index: 504310 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7793. Min Act: -0.0001

Data Index: 252339 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1122166 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7229. Min Act: -0.0001

Data Index: 557204 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1093520 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7166. Min Act: -0.0001

Data Index: 721563 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7129. Min Act: -0.0001

Data Index: 1276012 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6656. Min Act: -0.0001

Data Index: 144630 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1006945 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7457. Min Act: -0.0001

Data Index: 797413 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7261. Min Act: -0.0001

Data Index: 924123 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6724. Min Act: -0.0001

Data Index: 1012207 (C4 (Web Text))

Max Activating Token Index: 998