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

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

Neuron 1172 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: 1.0147. Min Range: -1.0147

Max Act: 1.0147. Min Act: -0.0001

Data Index: 1009802 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1143319 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8481. Min Act: -0.0001

Data Index: 587736 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8251. Min Act: -0.0001

Data Index: 331820 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8197. Min Act: -0.0001

Data Index: 794090 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8046. Min Act: -0.0001

Data Index: 801317 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8060. Min Act: -0.0001

Data Index: 409053 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1031010 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7557. Min Act: -0.0001

Data Index: 148483 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7523. Min Act: -0.0001

Data Index: 623362 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.8314. Min Act: -0.0001

Data Index: 974210 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6938. Min Act: -0.0001

Data Index: 143605 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7420. Min Act: -0.0001

Data Index: 138625 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6896. Min Act: -0.0001

Data Index: 1223715 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7268. Min Act: -0.0001

Data Index: 34959 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1281663 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6792. Min Act: -0.0001

Data Index: 348496 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6925. Min Act: -0.0001

Data Index: 1296202 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6453. Min Act: -0.0001

Data Index: 414689 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.0147. Min Range: -1.0147

Max Act: 0.6239. Min Act: -0.0001

Data Index: 541478 (C4 (Web Text))

Max Activating Token Index: 886