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

Dataset: The Pile

Neuron 1059 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1683838 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.1389. Min Act: -0.0000

Data Index: 837671 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.2300. Min Range: -1.2300

Max Act: 1.0282. Min Act: 0.0000

Data Index: 1968661 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1055864 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.9843. Min Act: -0.0000

Data Index: 304138 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1572643 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8932. Min Act: 0.0000

Data Index: 918724 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1131416 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1192354 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8660. Min Act: -0.0000

Data Index: 116789 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8369. Min Act: 0.0000

Data Index: 556259 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7355. Min Act: -0.0000

Data Index: 337183 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7858. Min Act: 0.0000

Data Index: 1737941 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1902581 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.8148. Min Act: -0.0000

Data Index: 497781 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1685118 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7509. Min Act: -0.0000

Data Index: 592024 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1447008 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1350619 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 1.2300. Min Range: -1.2300

Max Act: 0.7362. Min Act: -0.0000

Data Index: 439406 (The Pile)

Max Activating Token Index: 251