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

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

Neuron 202 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.5590. Min Act: -0.0001

Data Index: 1214026 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.3757. Min Act: -0.0001

Data Index: 1267565 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2951. Min Act: -0.0001

Data Index: 113168 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2905. Min Act: -0.0001

Data Index: 228085 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.4681. Min Act: -0.0001

Data Index: 892757 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.1489. Min Act: -0.0001

Data Index: 1279296 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.3550. Min Act: -0.0002

Data Index: 1196695 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2006. Min Act: -0.0001

Data Index: 1022465 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2213. Min Act: -0.0001

Data Index: 1187203 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2970. Min Act: -0.0001

Data Index: 622516 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2340. Min Act: -0.0001

Data Index: 1086331 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.1681. Min Act: -0.0001

Data Index: 944851 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.1872. Min Act: -0.0001

Data Index: 1050372 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.1417. Min Act: -0.0002

Data Index: 498902 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.3114. Min Act: -0.0001

Data Index: 992919 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2079. Min Act: -0.0001

Data Index: 278169 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.1738. Min Act: -0.0001

Data Index: 241679 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2381. Min Act: -0.0001

Data Index: 1259576 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2133. Min Act: -0.0002

Data Index: 166195 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 1.5590. Min Range: -1.5590

Max Act: 1.2380. Min Act: -0.0002

Data Index: 537124 (C4 (Web Text))

Max Activating Token Index: 647