Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1072168 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1667. Min Act: -0.0001

Data Index: 214522 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1517. Min Act: -0.0001

Data Index: 117646 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1492. Min Act: -0.0001

Data Index: 813514 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1419. Min Act: -0.0001

Data Index: 218545 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1353. Min Act: -0.0000

Data Index: 41972 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1115604 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1436. Min Act: -0.0001

Data Index: 663223 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1329. Min Act: -0.0000

Data Index: 143017 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1340. Min Act: -0.0001

Data Index: 93543 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1324. Min Act: 0.0000

Data Index: 388764 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1356. Min Act: -0.0001

Data Index: 74374 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1285. Min Act: -0.0001

Data Index: 732808 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1311301 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1226592 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1341. Min Act: -0.0001

Data Index: 651705 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1076587 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1281. Min Act: -0.0001

Data Index: 1238611 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1303. Min Act: -0.0001

Data Index: 70952 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.1882. Min Range: -0.1882

Max Act: 0.1201. Min Act: -0.0001

Data Index: 636617 (C4 (Web Text))

Max Activating Token Index: 314