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

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

Neuron 2555 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.6039. Min Act: -0.0000

Data Index: 1011663 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.5783. Min Act: -0.0000

Data Index: 320137 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.4531. Min Act: -0.0000

Data Index: 964930 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1034873 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3482. Min Act: -0.0000

Data Index: 731349 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3331. Min Act: -0.0000

Data Index: 990419 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2906. Min Act: -0.0000

Data Index: 787376 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2785. Min Act: -0.0000

Data Index: 479461 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3663. Min Act: -0.0000

Data Index: 659977 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3394. Min Act: -0.0000

Data Index: 260763 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2573. Min Act: -0.0000

Data Index: 526324 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1778. Min Act: -0.0000

Data Index: 159384 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2323. Min Act: -0.0000

Data Index: 443355 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2089. Min Act: -0.0000

Data Index: 746553 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2523. Min Act: -0.0000

Data Index: 14422 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1246573 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1196668 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1351725 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1123142 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1404335 (Python Code)

Max Activating Token Index: 633