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

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

Neuron 4070 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9968. Min Act: -0.0000

Data Index: 644173 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1101262 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.9066. Min Act: -0.0000

Data Index: 441525 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8414. Min Act: -0.0000

Data Index: 83442 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8375. Min Act: -0.0000

Data Index: 443080 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.6911. Min Act: -0.0000

Data Index: 682176 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1121681 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8364. Min Act: -0.0000

Data Index: 642226 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1306453 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8813. Min Act: -0.0000

Data Index: 602778 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1442539 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8375. Min Act: -0.0000

Data Index: 477418 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7967. Min Act: -0.0000

Data Index: 993408 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.8308. Min Act: -0.0000

Data Index: 819446 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7969. Min Act: -0.0000

Data Index: 269281 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7961. Min Act: -0.0000

Data Index: 660379 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7629. Min Act: -0.0000

Data Index: 558154 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1089747 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1147414 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.9968. Min Range: -0.9968

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1653486 (Python Code)

Max Activating Token Index: 898