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

Dataset: The Pile

Neuron 4405 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3542. Min Range: -3.3542

Max Act: 3.2162. Min Act: -0.0000

Data Index: 1410869 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 3.3542. Min Range: -3.3542

Max Act: 3.3542. Min Act: -0.0000

Data Index: 258588 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.7929. Min Act: -0.0000

Data Index: 972884 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.9778. Min Act: -0.0000

Data Index: 170880 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.9454. Min Act: -0.0000

Data Index: 1782114 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.7012. Min Act: -0.0000

Data Index: 25393 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.7714. Min Act: -0.0000

Data Index: 1230753 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.4653. Min Act: -0.0000

Data Index: 499261 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.9587. Min Act: -0.0000

Data Index: 860151 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.3533. Min Act: -0.0000

Data Index: 1317044 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1460992 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1460297 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.5560. Min Act: -0.0000

Data Index: 1956224 (The Pile)

Max Activating Token Index: 203

Text #13

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.6599. Min Act: -0.0000

Data Index: 1646903 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.5285. Min Act: -0.0000

Data Index: 584021 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.3229. Min Act: -0.0000

Data Index: 1921836 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.3593. Min Act: -0.0000

Data Index: 469605 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.4365. Min Act: -0.0000

Data Index: 182984 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1654224 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 3.3542. Min Range: -3.3542

Max Act: 2.5349. Min Act: -0.0000

Data Index: 1566884 (The Pile)

Max Activating Token Index: 820