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

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

Neuron 1158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.8815. Min Act: -0.0000

Data Index: 104940 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.7259. Min Act: -0.0001

Data Index: 188405 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.3984. Min Act: -0.0000

Data Index: 352007 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.3447. Min Act: -0.0001

Data Index: 532245 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.2463. Min Act: -0.0000

Data Index: 428160 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.2351. Min Act: -0.0001

Data Index: 405923 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1989. Min Act: -0.0000

Data Index: 259038 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1566. Min Act: -0.0000

Data Index: 217282 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.2616. Min Act: -0.0000

Data Index: 1111838 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1172. Min Act: -0.0000

Data Index: 688923 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0024. Min Act: -0.0000

Data Index: 998962 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1042. Min Act: -0.0000

Data Index: 283907 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.1214. Min Act: -0.0000

Data Index: 139829 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0889. Min Act: -0.0000

Data Index: 487322 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0681. Min Act: -0.0000

Data Index: 385029 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0645. Min Act: -0.0000

Data Index: 1126280 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0544. Min Act: -0.0000

Data Index: 693919 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 2.8815. Min Range: -2.8815

Max Act: 1.9318. Min Act: -0.0001

Data Index: 202993 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0284. Min Act: -0.0000

Data Index: 920552 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 2.8815. Min Range: -2.8815

Max Act: 2.0192. Min Act: -0.0000

Data Index: 365435 (C4 (Web Text))

Max Activating Token Index: 657