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

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

Neuron 3803 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: 0.2957. Min Range: -0.2957

Max Act: 0.2957. Min Act: -0.0001

Data Index: 777099 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1041330 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2585. Min Act: -0.0000

Data Index: 718784 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2360. Min Act: -0.0000

Data Index: 683664 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2244. Min Act: -0.0001

Data Index: 759434 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1077766 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2199. Min Act: -0.0001

Data Index: 555400 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2154. Min Act: -0.0001

Data Index: 7517 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2135. Min Act: -0.0001

Data Index: 409038 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2134. Min Act: -0.0001

Data Index: 977869 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1182951 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.1972. Min Act: -0.0001

Data Index: 303101 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2133. Min Act: -0.0001

Data Index: 75832 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2061. Min Act: -0.0001

Data Index: 552714 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.1900. Min Act: -0.0001

Data Index: 716531 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.1950. Min Act: -0.0001

Data Index: 621255 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2007. Min Act: -0.0001

Data Index: 853542 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1237513 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.1934. Min Act: -0.0000

Data Index: 794073 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.2957. Min Range: -0.2957

Max Act: 0.1970. Min Act: -0.0000

Data Index: 732064 (C4 (Web Text))

Max Activating Token Index: 331