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

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

Neuron 2544 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: 5.7443. Min Range: -5.7443

Max Act: 5.6122. Min Act: -0.0000

Data Index: 1442414 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 5.7443. Min Range: -5.7443

Max Act: 5.7443. Min Act: -0.0000

Data Index: 1652316 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 5.7443. Min Range: -5.7443

Max Act: 5.4010. Min Act: -0.0000

Data Index: 192739 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 5.7443. Min Range: -5.7443

Max Act: 5.3250. Min Act: -0.0000

Data Index: 479553 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.9352. Min Act: -0.0000

Data Index: 1646626 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 5.7443. Min Range: -5.7443

Max Act: 5.2207. Min Act: -0.0000

Data Index: 1612507 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.9941. Min Act: -0.0000

Data Index: 1397969 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.7282. Min Act: -0.0001

Data Index: 1528098 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 5.7443. Min Range: -5.7443

Max Act: 5.2074. Min Act: -0.0000

Data Index: 1595738 (Python Code)

Max Activating Token Index: 527

Text #9

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.8188. Min Act: -0.0000

Data Index: 1510852 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.9282. Min Act: -0.0000

Data Index: 1369071 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.9032. Min Act: -0.0000

Data Index: 1621726 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.9117. Min Act: -0.0000

Data Index: 1535859 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.3497. Min Act: -0.0000

Data Index: 1626538 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.8414. Min Act: -0.0000

Data Index: 1396761 (Python Code)

Max Activating Token Index: 625

Text #15

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.8116. Min Act: -0.0000

Data Index: 144699 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.6298. Min Act: -0.0000

Data Index: 1397980 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.4220. Min Act: -0.0000

Data Index: 1483366 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.7607. Min Act: -0.0000

Data Index: 1372430 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 5.7443. Min Range: -5.7443

Max Act: 4.5986. Min Act: -0.0000

Data Index: 1418852 (Python Code)

Max Activating Token Index: 447