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

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

Neuron 4213 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4288. Min Act: -0.0001

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3896. Min Act: -0.0001

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3434. Min Act: -0.0001

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3491. Min Act: -0.0001

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3355. Min Act: -0.0001

Data Index: 337599 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3055. Min Act: -0.0001

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3035. Min Act: -0.0001

Data Index: 422028 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3253. Min Act: -0.0001

Data Index: 133604 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3042. Min Act: -0.0001

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3085. Min Act: -0.0001

Data Index: 101269 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1357888 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2562. Min Act: -0.0001

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2718. Min Act: -0.0001

Data Index: 299420 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2608. Min Act: -0.0001

Data Index: 86760 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2493. Min Act: -0.0001

Data Index: 187180 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2473. Min Act: -0.0001

Data Index: 921329 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2440. Min Act: -0.0001

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2265. Min Act: -0.0001

Data Index: 992196 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1176694 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.2194. Min Act: -0.0001

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 613