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

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

Neuron 2321 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.8444. Min Act: -0.0001

Data Index: 78735 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.8863. Min Act: -0.0001

Data Index: 145451 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.8450. Min Act: -0.0001

Data Index: 1295816 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6241. Min Act: -0.0001

Data Index: 966976 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.7167. Min Act: -0.0001

Data Index: 1052316 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.7052. Min Act: -0.0001

Data Index: 54097 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6840. Min Act: -0.0001

Data Index: 1335130 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6883. Min Act: -0.0001

Data Index: 771031 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5928. Min Act: -0.0001

Data Index: 282158 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6780. Min Act: -0.0001

Data Index: 441351 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5805. Min Act: -0.0001

Data Index: 1052287 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6476. Min Act: -0.0001

Data Index: 1024677 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6233. Min Act: -0.0001

Data Index: 272872 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.7157. Min Act: -0.0001

Data Index: 286935 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.6039. Min Act: -0.0001

Data Index: 683744 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5986. Min Act: -0.0001

Data Index: 1351727 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5739. Min Act: -0.0001

Data Index: 643527 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5650. Min Act: -0.0001

Data Index: 676572 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.5681. Min Act: -0.0001

Data Index: 1211105 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.8863. Min Range: -1.8863

Max Act: 1.4739. Min Act: -0.0001

Data Index: 1323105 (C4 (Web Text))

Max Activating Token Index: 571