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

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

Neuron 1162 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1307. Min Act: -0.0000

Data Index: 401228 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.2131. Min Act: -0.0001

Data Index: 75214 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1957. Min Act: -0.0000

Data Index: 634269 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1670. Min Act: -0.0001

Data Index: 48948 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1197. Min Act: -0.0000

Data Index: 759028 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9972. Min Act: -0.0001

Data Index: 23120 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0025. Min Act: -0.0000

Data Index: 578057 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.1144. Min Act: -0.0000

Data Index: 894878 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9882. Min Act: -0.0000

Data Index: 890095 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0494. Min Act: -0.0001

Data Index: 736879 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9978. Min Act: -0.0001

Data Index: 1025194 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9221. Min Act: -0.0000

Data Index: 121264 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0320. Min Act: -0.0000

Data Index: 362691 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9345. Min Act: -0.0001

Data Index: 1201167 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0578. Min Act: -0.0001

Data Index: 882419 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9211. Min Act: -0.0000

Data Index: 396794 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9750. Min Act: -0.0000

Data Index: 675288 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.2131. Min Range: -1.2131

Max Act: 1.0109. Min Act: -0.0001

Data Index: 272751 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.9705. Min Act: -0.0001

Data Index: 339268 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.2131. Min Range: -1.2131

Max Act: 0.8755. Min Act: -0.0001

Data Index: 982933 (C4 (Web Text))

Max Activating Token Index: 998