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

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

Neuron 5450 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1021417 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1567. Min Act: -0.0000

Data Index: 973306 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1108257 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1380. Min Act: -0.0000

Data Index: 806002 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1135455 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1463. Min Act: -0.0000

Data Index: 861024 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1433. Min Act: -0.0000

Data Index: 537019 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1465. Min Act: -0.0000

Data Index: 369053 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1393. Min Act: -0.0000

Data Index: 52996 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1349. Min Act: -0.0000

Data Index: 823946 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1390. Min Act: -0.0000

Data Index: 434326 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1332. Min Act: -0.0000

Data Index: 641820 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1321. Min Act: -0.0000

Data Index: 290464 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1224996 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1386. Min Act: -0.0000

Data Index: 263795 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1152577 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1418. Min Act: -0.0000

Data Index: 362626 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1374. Min Act: -0.0000

Data Index: 579837 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1305. Min Act: -0.0000

Data Index: 355055 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1324. Min Act: -0.0000

Data Index: 236079 (C4 (Web Text))

Max Activating Token Index: 428