Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2089. Min Range: -3.2089

Max Act: 3.2089. Min Act: -0.0000

Data Index: 1171836 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.8114. Min Act: -0.0000

Data Index: 1134296 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.9439. Min Act: -0.0000

Data Index: 239205 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.9515. Min Act: -0.0000

Data Index: 1241938 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.7103. Min Act: -0.0000

Data Index: 580687 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.8156. Min Act: -0.0000

Data Index: 820752 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.6745. Min Act: -0.0000

Data Index: 326701 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.5624. Min Act: -0.0000

Data Index: 742850 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.5451. Min Act: -0.0000

Data Index: 1061537 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.3299. Min Act: -0.0000

Data Index: 179436 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.4206. Min Act: -0.0000

Data Index: 541052 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.4249. Min Act: -0.0000

Data Index: 501966 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.5151. Min Act: -0.0000

Data Index: 500407 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.2969. Min Act: -0.0000

Data Index: 66672 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 3.2089. Min Range: -3.2089

Max Act: 1.9174. Min Act: -0.0000

Data Index: 687032 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 3.2089. Min Range: -3.2089

Max Act: 1.9767. Min Act: -0.0000

Data Index: 812796 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.2089. Min Range: -3.2089

Max Act: 1.9797. Min Act: -0.0000

Data Index: 352573 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 3.2089. Min Range: -3.2089

Max Act: 1.8410. Min Act: -0.0000

Data Index: 664808 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.2089. Min Range: -3.2089

Max Act: 2.0395. Min Act: -0.0000

Data Index: 1185016 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.2089. Min Range: -3.2089

Max Act: 1.8656. Min Act: -0.0000

Data Index: 828465 (C4 (Web Text))

Max Activating Token Index: 855