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

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

Neuron 154 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: 3.1739. Min Range: -3.1739

Max Act: 3.1739. Min Act: -0.0000

Data Index: 674229 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.1739. Min Range: -3.1739

Max Act: 3.0209. Min Act: -0.0000

Data Index: 291446 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.4303. Min Act: -0.0000

Data Index: 108287 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.2425. Min Act: -0.0000

Data Index: 1372470 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.4379. Min Act: -0.0000

Data Index: 1381393 (Python Code)

Max Activating Token Index: 829

Text #5

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.4122. Min Act: -0.0000

Data Index: 705250 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.2227. Min Act: -0.0000

Data Index: 1323419 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.0766. Min Act: -0.0000

Data Index: 838208 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.2948. Min Act: -0.0000

Data Index: 46093 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.1406. Min Act: -0.0000

Data Index: 7521 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.2038. Min Act: -0.0000

Data Index: 817446 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.0506. Min Act: -0.0000

Data Index: 959059 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.0365. Min Act: -0.0000

Data Index: 45938 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.1259. Min Act: -0.0000

Data Index: 1073613 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.2044. Min Act: -0.0000

Data Index: 1037831 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.1300. Min Act: -0.0000

Data Index: 1434789 (Python Code)

Max Activating Token Index: 187

Text #17

Max Range: 3.1739. Min Range: -3.1739

Max Act: 1.8956. Min Act: -0.0000

Data Index: 615365 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.1739. Min Range: -3.1739

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1591834 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 3.1739. Min Range: -3.1739

Max Act: 2.0036. Min Act: -0.0000

Data Index: 1056657 (C4 (Web Text))

Max Activating Token Index: 482