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

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

Neuron 4827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1331702 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.2353. Min Act: -0.0000

Data Index: 513754 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1765. Min Act: -0.0000

Data Index: 439013 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1677. Min Act: -0.0000

Data Index: 436387 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1427325 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1336962 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1475918 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1644741 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1602324 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1019527 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1548. Min Act: -0.0000

Data Index: 701952 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1332. Min Act: -0.0000

Data Index: 752971 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1515859 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1226. Min Act: -0.0000

Data Index: 892358 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1448. Min Act: -0.0000

Data Index: 388441 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1372749 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1335. Min Act: -0.0000

Data Index: 241863 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1408. Min Act: -0.0000

Data Index: 320041 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1070226 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.2353. Min Range: -0.2353

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1313144 (C4 (Web Text))

Max Activating Token Index: 270