Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1478861 (Python Code)

Max Activating Token Index: 550

Text #1

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1125214 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1428093 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2997. Min Act: -0.0000

Data Index: 923425 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1117830 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2865. Min Act: -0.0000

Data Index: 917716 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2897. Min Act: -0.0000

Data Index: 13733 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2549. Min Act: -0.0000

Data Index: 533062 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2584. Min Act: -0.0000

Data Index: 302914 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1294652 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1576179 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1234558 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1421446 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1556177 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2431. Min Act: -0.0000

Data Index: 556899 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2432. Min Act: -0.0000

Data Index: 838426 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2236. Min Act: -0.0000

Data Index: 332389 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1356040 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2518. Min Act: -0.0000

Data Index: 600571 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1405325 (Python Code)

Max Activating Token Index: 138