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

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

Neuron 534 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.6598. Min Act: -0.0000

Data Index: 1353864 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.7835. Min Act: -0.0000

Data Index: 361520 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.5145. Min Act: -0.0000

Data Index: 132525 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.3572. Min Act: -0.0000

Data Index: 202214 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.6542. Min Act: -0.0000

Data Index: 1088782 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.3585. Min Act: -0.0000

Data Index: 4814 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.2518. Min Act: -0.0000

Data Index: 604934 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 7.7835. Min Range: -7.7835

Max Act: 7.1631. Min Act: -0.0000

Data Index: 1286401 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 7.7835. Min Range: -7.7835

Max Act: 6.9598. Min Act: -0.0000

Data Index: 216415 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 7.7835. Min Range: -7.7835

Max Act: 6.6627. Min Act: -0.0000

Data Index: 728918 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 7.7835. Min Range: -7.7835

Max Act: 6.1999. Min Act: -0.0000

Data Index: 650887 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 7.7835. Min Range: -7.7835

Max Act: 5.5876. Min Act: -0.0000

Data Index: 556664 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 7.7835. Min Range: -7.7835

Max Act: 5.5791. Min Act: -0.0000

Data Index: 244243 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 7.7835. Min Range: -7.7835

Max Act: 5.5669. Min Act: -0.0000

Data Index: 1153192 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 7.7835. Min Range: -7.7835

Max Act: 5.3779. Min Act: 0.0000

Data Index: 82535 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 7.7835. Min Range: -7.7835

Max Act: 4.2288. Min Act: -0.0000

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 7.7835. Min Range: -7.7835

Max Act: 4.3778. Min Act: -0.0000

Data Index: 844718 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 7.7835. Min Range: -7.7835

Max Act: 4.4265. Min Act: -0.0000

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 7.7835. Min Range: -7.7835

Max Act: 4.3756. Min Act: -0.0000

Data Index: 128376 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 7.7835. Min Range: -7.7835

Max Act: 4.4870. Min Act: -0.0000

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 467