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

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

Neuron 3740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1075505 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.0019. Min Range: -1.0019

Max Act: 1.0019. Min Act: -0.0000

Data Index: 1218615 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1209579 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8623. Min Act: -0.0000

Data Index: 650413 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8494. Min Act: -0.0000

Data Index: 425055 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8419. Min Act: -0.0000

Data Index: 700592 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8365. Min Act: -0.0000

Data Index: 81485 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8125. Min Act: -0.0000

Data Index: 700545 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.8113. Min Act: -0.0000

Data Index: 824147 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1400181 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7838. Min Act: -0.0000

Data Index: 199509 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7849. Min Act: -0.0000

Data Index: 812105 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1058324 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7424. Min Act: -0.0000

Data Index: 882093 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7671. Min Act: -0.0000

Data Index: 378058 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7842. Min Act: -0.0000

Data Index: 343250 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7381. Min Act: -0.0000

Data Index: 276266 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.7348. Min Act: -0.0000

Data Index: 46716 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1225501 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.0019. Min Range: -1.0019

Max Act: 0.6817. Min Act: -0.0000

Data Index: 51145 (C4 (Web Text))

Max Activating Token Index: 825