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

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

Neuron 3751 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: 3.5469. Min Range: -3.5469

Max Act: 3.5469. Min Act: -0.0000

Data Index: 162301 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 3.5469. Min Range: -3.5469

Max Act: 3.3288. Min Act: -0.0000

Data Index: 1166202 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.6386. Min Act: -0.0000

Data Index: 24601 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.7701. Min Act: -0.0000

Data Index: 55672 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.6968. Min Act: -0.0000

Data Index: 856001 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.7012. Min Act: -0.0000

Data Index: 734147 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.6928. Min Act: -0.0000

Data Index: 926842 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.5482. Min Act: -0.0000

Data Index: 3114 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.5978. Min Act: -0.0000

Data Index: 1210551 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.7062. Min Act: -0.0000

Data Index: 763913 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1028541 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.5296. Min Act: -0.0000

Data Index: 890110 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.3944. Min Act: -0.0000

Data Index: 798327 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.5205. Min Act: -0.0000

Data Index: 160955 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.5050. Min Act: -0.0000

Data Index: 630790 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.3351. Min Act: -0.0000

Data Index: 827116 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.4277. Min Act: -0.0000

Data Index: 334828 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.4280. Min Act: -0.0000

Data Index: 1317779 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.2969. Min Act: -0.0000

Data Index: 1144629 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 3.5469. Min Range: -3.5469

Max Act: 2.3593. Min Act: -0.0000

Data Index: 225833 (C4 (Web Text))

Max Activating Token Index: 49