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

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

Neuron 1353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.1135. Min Act: -0.0002

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.2090. Min Act: -0.0001

Data Index: 301561 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1400751 (Python Code)

Max Activating Token Index: 961

Text #3

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1537476 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1510336 (Python Code)

Max Activating Token Index: 969

Text #5

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1864. Min Act: -0.0001

Data Index: 677720 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.2051. Min Act: -0.0001

Data Index: 1622114 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1152289 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1649566 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1557487 (Python Code)

Max Activating Token Index: 923

Text #10

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1379845 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1581358 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1597417 (Python Code)

Max Activating Token Index: 1014

Text #13

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1625988 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1811. Min Act: -0.0001

Data Index: 983376 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1623. Min Act: -0.0001

Data Index: 331742 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1515554 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1212540 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1509220 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1408365 (Python Code)

Max Activating Token Index: 988