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

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

Neuron 1417 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1450549 (Python Code)

Max Activating Token Index: 774

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7513. Min Act: -0.0001

Data Index: 1598911 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5078. Min Act: -0.0001

Data Index: 1485956 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5688. Min Act: -0.0000

Data Index: 142466 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6349. Min Act: -0.0001

Data Index: 1422335 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1484809 (Python Code)

Max Activating Token Index: 600

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4323. Min Act: -0.0001

Data Index: 1493154 (Python Code)

Max Activating Token Index: 422

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4482. Min Act: -0.0000

Data Index: 853934 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1486546 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4275. Min Act: -0.0001

Data Index: 1574360 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1611956 (Python Code)

Max Activating Token Index: 288

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3945. Min Act: 0.0000

Data Index: 669256 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3748. Min Act: -0.0000

Data Index: 639383 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1648567 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3904. Min Act: -0.0000

Data Index: 729674 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3637. Min Act: -0.0000

Data Index: 851091 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3316. Min Act: -0.0000

Data Index: 147739 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1326556 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1649133 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1240215 (C4 (Web Text))

Max Activating Token Index: 746