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

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

Neuron 5987 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: 0.6001. Min Range: -0.6001

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1618295 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1645759 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1375481 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1273538 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1616018 (Python Code)

Max Activating Token Index: 884

Text #5

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.4324. Min Act: -0.0000

Data Index: 351860 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1627488 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1389100 (Python Code)

Max Activating Token Index: 918

Text #8

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.4082. Min Act: -0.0000

Data Index: 371622 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3737. Min Act: -0.0000

Data Index: 875422 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1502865 (Python Code)

Max Activating Token Index: 816

Text #11

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1534352 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1379578 (Python Code)

Max Activating Token Index: 792

Text #13

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1557157 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1557685 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1477528 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1614559 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1585793 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1482642 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 0.6001. Min Range: -0.6001

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1378709 (Python Code)

Max Activating Token Index: 811