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

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

Neuron 1799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1353. Min Range: -1.1353

Max Act: 1.1353. Min Act: -0.0001

Data Index: 443729 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.1353. Min Range: -1.1353

Max Act: 1.1146. Min Act: -0.0001

Data Index: 609410 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.1353. Min Range: -1.1353

Max Act: 1.0235. Min Act: -0.0001

Data Index: 620415 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.9832. Min Act: -0.0001

Data Index: 725697 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.9783. Min Act: -0.0001

Data Index: 580647 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.9070. Min Act: -0.0001

Data Index: 439020 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1245394 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.9445. Min Act: -0.0001

Data Index: 592391 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8350. Min Act: -0.0001

Data Index: 371407 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1290570 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8837. Min Act: -0.0001

Data Index: 240494 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8796. Min Act: -0.0001

Data Index: 909387 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8815. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8673. Min Act: -0.0001

Data Index: 714033 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8566. Min Act: -0.0001

Data Index: 800248 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8336. Min Act: -0.0000

Data Index: 63078 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8247. Min Act: -0.0001

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1187936 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.8017. Min Act: -0.0001

Data Index: 696109 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 1.1353. Min Range: -1.1353

Max Act: 0.7970. Min Act: -0.0001

Data Index: 101669 (C4 (Web Text))

Max Activating Token Index: 131