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

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

Neuron 194 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: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0001

Data Index: 134280 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1522. Min Act: -0.0001

Data Index: 165981 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1495. Min Act: -0.0001

Data Index: 641037 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1334. Min Act: -0.0001

Data Index: 736966 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1047954 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1415. Min Act: -0.0001

Data Index: 966678 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1447. Min Act: -0.0001

Data Index: 462012 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1550. Min Act: -0.0001

Data Index: 851308 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1374. Min Act: -0.0001

Data Index: 376280 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1278168 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1277. Min Act: -0.0001

Data Index: 365017 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1466. Min Act: -0.0001

Data Index: 854758 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1455. Min Act: -0.0001

Data Index: 987472 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1327343 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1365. Min Act: -0.0001

Data Index: 749383 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1362. Min Act: -0.0001

Data Index: 999648 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1457. Min Act: -0.0001

Data Index: 824745 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1413. Min Act: -0.0001

Data Index: 259241 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1101646 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1168984 (C4 (Web Text))

Max Activating Token Index: 809