Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1188 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: 0.0000

Data Index: 1615770 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1197379 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3305. Min Act: 0.0000

Data Index: 610524 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2959. Min Act: -0.0000

Data Index: 1334264 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1615209 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2198. Min Act: 0.0000

Data Index: 1343918 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2102. Min Act: 0.0000

Data Index: 27847 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1469591 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2296. Min Act: -0.0000

Data Index: 1580076 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1290209 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1542904 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1873. Min Act: 0.0000

Data Index: 385870 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0835. Min Act: -0.0000

Data Index: 585686 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1058339 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1488215 (Python Code)

Max Activating Token Index: 538

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1428. Min Act: -0.0000

Data Index: 367838 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1439. Min Act: -0.0000

Data Index: 957350 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1312. Min Act: 0.0000

Data Index: 1160535 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1336. Min Act: 0.0000

Data Index: 1369129 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1394888 (Python Code)

Max Activating Token Index: 444