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

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

Neuron 3223 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: 0.1536. Min Range: -0.1536

Max Act: 0.1422. Min Act: -0.0000

Data Index: 187920 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0000

Data Index: 940121 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1559831 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1454. Min Act: -0.0001

Data Index: 927259 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1481. Min Act: -0.0000

Data Index: 531638 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1375. Min Act: -0.0000

Data Index: 215612 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1313. Min Act: -0.0000

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1582434 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1372. Min Act: -0.0000

Data Index: 902744 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1241. Min Act: -0.0000

Data Index: 881561 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1231. Min Act: -0.0000

Data Index: 823680 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1324. Min Act: -0.0000

Data Index: 822811 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1262. Min Act: -0.0000

Data Index: 995889 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1275922 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1067. Min Act: -0.0000

Data Index: 355521 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1227757 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1641338 (Python Code)

Max Activating Token Index: 605

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1204. Min Act: -0.0000

Data Index: 891321 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1206. Min Act: -0.0000

Data Index: 890692 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1005. Min Act: -0.0000

Data Index: 347152 (C4 (Web Text))

Max Activating Token Index: 804