Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 306 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1458759 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1128487 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1448725 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1473243 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0001

Data Index: 281348 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1595. Min Act: -0.0001

Data Index: 217760 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1306. Min Act: -0.0001

Data Index: 457881 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1343. Min Act: -0.0001

Data Index: 97683 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1364. Min Act: -0.0001

Data Index: 873315 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1457. Min Act: -0.0001

Data Index: 575225 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1393. Min Act: -0.0001

Data Index: 629622 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1380. Min Act: -0.0001

Data Index: 699623 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1365120 (Python Code)

Max Activating Token Index: 870

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1544545 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1493. Min Act: -0.0001

Data Index: 218296 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1573917 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1328446 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1431. Min Act: -0.0001

Data Index: 925928 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1126775 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1603903 (Python Code)

Max Activating Token Index: 474