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

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

Neuron 2218 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: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1369. Min Act: -0.0001

Data Index: 976812 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1427. Min Act: -0.0001

Data Index: 260508 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1010. Min Act: -0.0001

Data Index: 75920 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1021833 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1348958 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0834. Min Act: -0.0001

Data Index: 1159192 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0860. Min Act: -0.0000

Data Index: 775007 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0807. Min Act: -0.0001

Data Index: 186048 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0829. Min Act: -0.0001

Data Index: 950189 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0810. Min Act: -0.0001

Data Index: 665818 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1230626 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0846. Min Act: -0.0001

Data Index: 165459 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0809. Min Act: -0.0000

Data Index: 254190 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0782. Min Act: -0.0001

Data Index: 399852 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0779. Min Act: -0.0001

Data Index: 660683 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0777. Min Act: -0.0001

Data Index: 97607 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1357112 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0766. Min Act: -0.0001

Data Index: 59099 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0785. Min Act: -0.0000

Data Index: 439994 (C4 (Web Text))

Max Activating Token Index: 303