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

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

Neuron 3376 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8412. Min Act: -0.0001

Data Index: 499583 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8157. Min Act: -0.0001

Data Index: 893434 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7890. Min Act: -0.0001

Data Index: 189114 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6956. Min Act: -0.0001

Data Index: 1276328 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7015. Min Act: -0.0001

Data Index: 834102 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6948. Min Act: -0.0001

Data Index: 803218 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6074. Min Act: -0.0001

Data Index: 432975 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1165448 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5663. Min Act: -0.0001

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5986. Min Act: -0.0001

Data Index: 881925 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5699. Min Act: -0.0001

Data Index: 711146 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5861. Min Act: -0.0001

Data Index: 250745 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5658. Min Act: -0.0001

Data Index: 357499 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5572. Min Act: -0.0001

Data Index: 392452 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5659. Min Act: -0.0001

Data Index: 92726 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5459. Min Act: -0.0001

Data Index: 675547 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5556. Min Act: -0.0001

Data Index: 66941 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5199. Min Act: -0.0001

Data Index: 672137 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5524. Min Act: -0.0001

Data Index: 296624 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5348. Min Act: -0.0001

Data Index: 943908 (C4 (Web Text))

Max Activating Token Index: 110