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

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

Neuron 3475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1361619 (Python Code)

Max Activating Token Index: 884

Text #1

Max Range: 2.0089. Min Range: -2.0089

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1472416 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1458550 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.5119. Min Act: -0.0000

Data Index: 300885 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1471793 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1586343 (Python Code)

Max Activating Token Index: 217

Text #6

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1642666 (Python Code)

Max Activating Token Index: 982

Text #7

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1501795 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1499097 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1522936 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.6437. Min Act: -0.0000

Data Index: 90757 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1525658 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1638801 (Python Code)

Max Activating Token Index: 988

Text #13

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.4017. Min Act: -0.0000

Data Index: 1448325 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.3933. Min Act: -0.0000

Data Index: 645527 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1586763 (Python Code)

Max Activating Token Index: 670

Text #16

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1195941 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.3902. Min Act: -0.0000

Data Index: 1102269 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.4224. Min Act: -0.0000

Data Index: 469861 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 2.0089. Min Range: -2.0089

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1242233 (C4 (Web Text))

Max Activating Token Index: 114