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

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

Neuron 286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1150708 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2240. Min Act: -0.0000

Data Index: 708152 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1127385 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1258232 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1778. Min Act: -0.0000

Data Index: 173394 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1696. Min Act: -0.0000

Data Index: 227926 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1619. Min Act: -0.0000

Data Index: 740652 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1720. Min Act: -0.0000

Data Index: 489544 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1065329 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1509. Min Act: -0.0000

Data Index: 615916 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1479. Min Act: -0.0000

Data Index: 453928 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1544. Min Act: -0.0000

Data Index: 931346 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1475. Min Act: -0.0000

Data Index: 398170 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1018258 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1446. Min Act: -0.0000

Data Index: 43633 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1331526 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1482723 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1393. Min Act: -0.0000

Data Index: 395379 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1463. Min Act: -0.0001

Data Index: 591125 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 0.2444. Min Range: -0.2444

Max Act: 0.1365. Min Act: -0.0000

Data Index: 52463 (C4 (Web Text))

Max Activating Token Index: 344