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

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

Neuron 2827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0197. Min Range: -1.0197

Max Act: 1.0197. Min Act: -0.0001

Data Index: 456268 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.9151. Min Act: -0.0000

Data Index: 698478 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.8326. Min Act: -0.0000

Data Index: 459936 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.8427. Min Act: -0.0001

Data Index: 280858 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7483. Min Act: -0.0001

Data Index: 470045 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7283. Min Act: -0.0001

Data Index: 332810 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7548. Min Act: -0.0001

Data Index: 963141 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7568. Min Act: -0.0001

Data Index: 476586 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7738. Min Act: -0.0000

Data Index: 546645 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7448. Min Act: -0.0001

Data Index: 1021707 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.6897. Min Act: -0.0001

Data Index: 606814 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7576. Min Act: -0.0000

Data Index: 592720 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7080. Min Act: -0.0001

Data Index: 238275 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7218. Min Act: -0.0001

Data Index: 405277 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.6753. Min Act: -0.0001

Data Index: 1143445 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7385. Min Act: -0.0000

Data Index: 87852 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7728. Min Act: -0.0000

Data Index: 962309 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.6603. Min Act: -0.0001

Data Index: 725820 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1194104 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.0197. Min Range: -1.0197

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1326782 (C4 (Web Text))

Max Activating Token Index: 276