Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2324. Min Act: -0.0000

Data Index: 975102 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1986. Min Act: -0.0001

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1831. Min Act: -0.0000

Data Index: 974737 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1763. Min Act: -0.0000

Data Index: 92050 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1494300 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1037275 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1650. Min Act: -0.0001

Data Index: 458782 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1416. Min Act: -0.0000

Data Index: 873006 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1501. Min Act: -0.0000

Data Index: 915119 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1471. Min Act: -0.0000

Data Index: 153620 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1460. Min Act: -0.0000

Data Index: 462357 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1246627 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1543. Min Act: -0.0000

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1369. Min Act: -0.0000

Data Index: 278080 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1018594 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1439. Min Act: -0.0000

Data Index: 403626 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1354. Min Act: -0.0000

Data Index: 271202 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1339. Min Act: -0.0000

Data Index: 568479 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1278. Min Act: -0.0000

Data Index: 785611 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1098365 (C4 (Web Text))

Max Activating Token Index: 585