Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2470 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1005876 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.8049. Min Act: -0.0000

Data Index: 298208 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.6167. Min Act: -0.0000

Data Index: 295246 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4722. Min Act: -0.0000

Data Index: 598941 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4510. Min Act: 0.0000

Data Index: 614155 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5260. Min Act: -0.0000

Data Index: 194471 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1212935 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1031494 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1080343 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3424. Min Act: -0.0000

Data Index: 755784 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3393. Min Act: 0.0000

Data Index: 1245766 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4092. Min Act: -0.0000

Data Index: 937930 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3115. Min Act: -0.0000

Data Index: 580019 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3122. Min Act: 0.0000

Data Index: 971159 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3071. Min Act: -0.0000

Data Index: 591908 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1202752 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1345504 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2986. Min Act: 0.0000

Data Index: 938216 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3126. Min Act: -0.0000

Data Index: 731681 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2824. Min Act: -0.0000

Data Index: 770557 (C4 (Web Text))

Max Activating Token Index: 958