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

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

Neuron 921 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: 1.5424. Min Range: -1.5424

Max Act: 1.5424. Min Act: -0.0001

Data Index: 106416 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3483. Min Act: -0.0001

Data Index: 859106 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3109. Min Act: -0.0001

Data Index: 390078 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3296. Min Act: -0.0001

Data Index: 1012971 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3269. Min Act: -0.0001

Data Index: 244900 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3640. Min Act: -0.0001

Data Index: 1293510 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.4329. Min Act: -0.0001

Data Index: 712577 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2706. Min Act: -0.0001

Data Index: 977095 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3246. Min Act: -0.0001

Data Index: 340504 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3854. Min Act: -0.0001

Data Index: 788385 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2921. Min Act: -0.0001

Data Index: 380545 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2974. Min Act: -0.0001

Data Index: 842404 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3563. Min Act: -0.0001

Data Index: 600137 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2727. Min Act: -0.0001

Data Index: 899038 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2628. Min Act: -0.0001

Data Index: 376231 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2553. Min Act: -0.0001

Data Index: 80958 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.3239. Min Act: -0.0001

Data Index: 522954 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.0722. Min Act: -0.0001

Data Index: 111707 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2444. Min Act: -0.0001

Data Index: 1217117 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.5424. Min Range: -1.5424

Max Act: 1.2582. Min Act: -0.0001

Data Index: 848724 (C4 (Web Text))

Max Activating Token Index: 907