Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1592. Min Act: -0.0002

Data Index: 936590 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1407982 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1485. Min Act: -0.0002

Data Index: 1172008 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1389. Min Act: -0.0002

Data Index: 957266 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1201337 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1434. Min Act: -0.0002

Data Index: 995100 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1550. Min Act: -0.0002

Data Index: 702839 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1319. Min Act: -0.0002

Data Index: 1132936 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1362. Min Act: -0.0002

Data Index: 375688 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1552. Min Act: -0.0002

Data Index: 275648 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1341. Min Act: -0.0002

Data Index: 679679 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1390. Min Act: -0.0002

Data Index: 63910 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1327. Min Act: -0.0002

Data Index: 655968 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1304. Min Act: -0.0002

Data Index: 858949 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1321. Min Act: -0.0002

Data Index: 468291 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1074524 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1253. Min Act: -0.0002

Data Index: 32503 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1580443 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1279. Min Act: -0.0002

Data Index: 899926 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.1592. Min Range: -0.1592

Max Act: 0.1276. Min Act: -0.0002

Data Index: 699415 (C4 (Web Text))

Max Activating Token Index: 600