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

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

Neuron 4660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.1169. Min Act: -0.0000

Data Index: 345049 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1352276 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1314141 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1115611 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1087627 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1225583 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0756. Min Act: -0.0000

Data Index: 709258 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0722. Min Act: -0.0000

Data Index: 324733 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0729. Min Act: -0.0000

Data Index: 36400 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1268982 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0689. Min Act: -0.0000

Data Index: 304447 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0671. Min Act: -0.0000

Data Index: 87808 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0662. Min Act: -0.0000

Data Index: 376015 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0658. Min Act: -0.0000

Data Index: 533377 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0727. Min Act: -0.0000

Data Index: 44666 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0696. Min Act: -0.0000

Data Index: 942307 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0670. Min Act: -0.0000

Data Index: 930657 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0622. Min Act: -0.0000

Data Index: 15404 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1081782 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1169. Min Range: -0.1169

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1353129 (C4 (Web Text))

Max Activating Token Index: 619