Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1965 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8052. Min Range: -4.8052

Max Act: 4.8052. Min Act: -0.0000

Data Index: 448524 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 4.8052. Min Range: -4.8052

Max Act: 3.0199. Min Act: -0.0000

Data Index: 1090258 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 4.8052. Min Range: -4.8052

Max Act: 3.1588. Min Act: -0.0000

Data Index: 385018 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 4.8052. Min Range: -4.8052

Max Act: 3.1031. Min Act: -0.0000

Data Index: 481755 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 4.8052. Min Range: -4.8052

Max Act: 3.0101. Min Act: -0.0001

Data Index: 845343 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.9291. Min Act: -0.0000

Data Index: 20149 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.7304. Min Act: -0.0000

Data Index: 1044535 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.9997. Min Act: -0.0000

Data Index: 1110244 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.7291. Min Act: -0.0000

Data Index: 372046 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.8187. Min Act: -0.0001

Data Index: 222782 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.9025. Min Act: -0.0000

Data Index: 293803 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.5310. Min Act: -0.0000

Data Index: 472995 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.8129. Min Act: -0.0001

Data Index: 99211 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.6053. Min Act: -0.0000

Data Index: 701433 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.7259. Min Act: -0.0000

Data Index: 319877 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.5908. Min Act: -0.0000

Data Index: 1107765 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.4747. Min Act: -0.0000

Data Index: 73865 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.6870. Min Act: -0.0000

Data Index: 1074805 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.2246. Min Act: -0.0000

Data Index: 428471 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 4.8052. Min Range: -4.8052

Max Act: 2.6878. Min Act: -0.0000

Data Index: 757148 (C4 (Web Text))

Max Activating Token Index: 662