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

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

Neuron 1438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.3823. Min Act: -0.0000

Data Index: 1087975 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.3262. Min Act: -0.0000

Data Index: 12924 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.1909. Min Act: -0.0000

Data Index: 694507 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.2539. Min Act: -0.0000

Data Index: 1027507 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.0656. Min Act: -0.0000

Data Index: 464116 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.1394. Min Act: -0.0000

Data Index: 434456 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.9084. Min Act: -0.0000

Data Index: 865242 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.0703. Min Act: -0.0000

Data Index: 200436 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.0141. Min Act: -0.0000

Data Index: 896397 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.9589. Min Act: -0.0000

Data Index: 628811 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.8964. Min Act: -0.0000

Data Index: 1349883 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.0086. Min Act: -0.0000

Data Index: 996708 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.8595. Min Act: -0.0000

Data Index: 743705 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.3823. Min Range: -3.3823

Max Act: 3.1084. Min Act: -0.0000

Data Index: 580809 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.6371. Min Act: -0.0000

Data Index: 109726 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.6511. Min Act: -0.0000

Data Index: 1344975 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.6765. Min Act: -0.0000

Data Index: 367890 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.5349. Min Act: -0.0000

Data Index: 429142 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.6191. Min Act: -0.0000

Data Index: 1332642 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.3823. Min Range: -3.3823

Max Act: 2.4852. Min Act: -0.0000

Data Index: 706044 (C4 (Web Text))

Max Activating Token Index: 428