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

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

Neuron 2122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.3975. Min Act: -0.0000

Data Index: 1563630 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1581092 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1438159 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1300919 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1496703 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.1761. Min Act: -0.0000

Data Index: 849331 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1485399 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1467869 (Python Code)

Max Activating Token Index: 388

Text #8

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1583152 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.0288. Min Act: -0.0000

Data Index: 436258 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.3975. Min Range: -1.3975

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1464719 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9795. Min Act: -0.0000

Data Index: 660770 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1433664 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1635123 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.8924. Min Act: -0.0000

Data Index: 348947 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.8288. Min Act: 0.0001

Data Index: 1608085 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1522978 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1632291 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1507564 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 1.3975. Min Range: -1.3975

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1489599 (Python Code)

Max Activating Token Index: 58