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

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

Neuron 2407 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1582613 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1423151 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1633467 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1629201 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1569165 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1616735 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1490569 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1384325 (Python Code)

Max Activating Token Index: 951

Text #8

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5006. Min Act: -0.0001

Data Index: 48842 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1563116 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1379781 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1586223 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1434322 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1560822 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1394401 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1594144 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1490218 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1469766 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1597324 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 0.6680. Min Range: -0.6680

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1616471 (Python Code)

Max Activating Token Index: 296