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

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

Neuron 3964 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: 0.3647. Min Range: -0.3647

Max Act: 0.3647. Min Act: -0.0000

Data Index: 126829 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1233450 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3228. Min Act: -0.0000

Data Index: 909850 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3256. Min Act: -0.0000

Data Index: 514587 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3272. Min Act: -0.0000

Data Index: 544893 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3264. Min Act: -0.0000

Data Index: 499374 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1050069 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1239708 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3112. Min Act: -0.0000

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1290175 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2887. Min Act: -0.0000

Data Index: 690068 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1242966 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1236595 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1268331 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2351. Min Act: -0.0000

Data Index: 134874 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1122132 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2416. Min Act: -0.0001

Data Index: 409634 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1176704 (C4 (Web Text))

Max Activating Token Index: 544