Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2553 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1173515 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1267945 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0485. Min Act: -0.0001

Data Index: 1633917 (Python Code)

Max Activating Token Index: 434

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0541. Min Act: -0.0001

Data Index: 977711 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1482674 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1519004 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0498. Min Act: -0.0001

Data Index: 649392 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1276479 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1580631 (Python Code)

Max Activating Token Index: 891

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1635856 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0437. Min Act: -0.0001

Data Index: 1449984 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1381049 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0474. Min Act: -0.0001

Data Index: 1436155 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0466. Min Act: -0.0001

Data Index: 329975 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0378. Min Act: -0.0001

Data Index: 871369 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1417963 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0427. Min Act: -0.0001

Data Index: 707187 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1563541 (Python Code)

Max Activating Token Index: 428

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1396108 (Python Code)

Max Activating Token Index: 842