Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 328 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3388. Min Range: -1.3388

Max Act: 1.3388. Min Act: -0.0000

Data Index: 434521 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1298257 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9637. Min Act: -0.0000

Data Index: 481065 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1171871 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9112. Min Act: -0.0000

Data Index: 304761 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9886. Min Act: -0.0000

Data Index: 866212 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1985033 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1218552 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8600. Min Act: -0.0000

Data Index: 384687 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1917621 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 1.3388. Min Range: -1.3388

Max Act: 1.0431. Min Act: -0.0000

Data Index: 212520 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1871805 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1787069 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8693. Min Act: -0.0000

Data Index: 227379 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1065402 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8410. Min Act: -0.0000

Data Index: 161845 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1629235 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1415465 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1384532 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 1.3388. Min Range: -1.3388

Max Act: 0.8371. Min Act: -0.0000

Data Index: 355971 (The Pile)

Max Activating Token Index: 135