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

Dataset: The Pile

Neuron 2030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0033. Min Range: -1.0033

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1337317 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1981988 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1341936 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1224370 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8758. Min Act: -0.0000

Data Index: 772256 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8096. Min Act: -0.0000

Data Index: 720416 (The Pile)

Max Activating Token Index: 190

Text #6

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1896573 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8467. Min Act: -0.0000

Data Index: 703392 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7894. Min Act: -0.0000

Data Index: 955192 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8124. Min Act: -0.0000

Data Index: 900879 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1728530 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1934341 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7514. Min Act: -0.0000

Data Index: 893001 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7479. Min Act: -0.0000

Data Index: 918344 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7655. Min Act: -0.0000

Data Index: 225657 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1824486 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1962280 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7556. Min Act: -0.0000

Data Index: 111647 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7973. Min Act: -0.0000

Data Index: 417584 (The Pile)

Max Activating Token Index: 965

Text #19

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1158858 (The Pile)

Max Activating Token Index: 245