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

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

Neuron 1481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.4561. Min Act: -0.0001

Data Index: 1081209 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3555. Min Act: -0.0001

Data Index: 604399 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.4240. Min Act: -0.0001

Data Index: 355976 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3288. Min Act: -0.0001

Data Index: 851043 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.3105. Min Act: -0.0001

Data Index: 262585 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1341. Min Act: -0.0001

Data Index: 673600 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2277. Min Act: -0.0001

Data Index: 1173116 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1285876 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2165. Min Act: -0.0001

Data Index: 799418 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2150. Min Act: -0.0001

Data Index: 445751 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1943. Min Act: -0.0001

Data Index: 556044 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1508. Min Act: -0.0001

Data Index: 596033 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.0917. Min Act: -0.0001

Data Index: 1019296 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1809. Min Act: -0.0001

Data Index: 703564 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2204. Min Act: -0.0001

Data Index: 1281258 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2138. Min Act: -0.0001

Data Index: 811840 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1368. Min Act: -0.0001

Data Index: 902593 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.1384. Min Act: -0.0001

Data Index: 140639 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.2121. Min Act: -0.0001

Data Index: 1076503 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.4561. Min Range: -1.4561

Max Act: 1.0968. Min Act: -0.0001

Data Index: 172312 (C4 (Web Text))

Max Activating Token Index: 321