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

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

Neuron 3146 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: 4.5217. Min Range: -4.5217

Max Act: 4.5217. Min Act: -0.0000

Data Index: 772246 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.1372. Min Act: -0.0000

Data Index: 630932 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.4211. Min Act: -0.0000

Data Index: 557898 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.9156. Min Act: -0.0000

Data Index: 706997 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.7712. Min Act: -0.0000

Data Index: 629946 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.8951. Min Act: -0.0000

Data Index: 822005 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5542. Min Act: -0.0000

Data Index: 919048 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5642. Min Act: -0.0000

Data Index: 234058 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5369. Min Act: -0.0000

Data Index: 701375 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.8518. Min Act: -0.0000

Data Index: 1128329 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.6858. Min Act: -0.0000

Data Index: 792024 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5078. Min Act: -0.0000

Data Index: 1240212 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.6436. Min Act: -0.0000

Data Index: 334196 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1291571 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.8861. Min Act: -0.0000

Data Index: 407216 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5213. Min Act: -0.0000

Data Index: 789055 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.3782. Min Act: -0.0000

Data Index: 1291881 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.3638. Min Act: -0.0000

Data Index: 125819 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.3350. Min Act: -0.0000

Data Index: 1238668 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 4.5217. Min Range: -4.5217

Max Act: 3.5003. Min Act: -0.0000

Data Index: 887284 (C4 (Web Text))

Max Activating Token Index: 36