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

Dataset: The Pile

Neuron 4179 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4906. Min Range: -5.4906

Max Act: 5.4906. Min Act: -0.0000

Data Index: 1082318 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 5.4906. Min Range: -5.4906

Max Act: 5.2186. Min Act: -0.0000

Data Index: 1128893 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 5.4906. Min Range: -5.4906

Max Act: 5.2931. Min Act: -0.0000

Data Index: 347540 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 5.4906. Min Range: -5.4906

Max Act: 4.8835. Min Act: -0.0000

Data Index: 808370 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 5.4906. Min Range: -5.4906

Max Act: 4.5513. Min Act: -0.0000

Data Index: 1880226 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 5.4906. Min Range: -5.4906

Max Act: 4.2943. Min Act: -0.0000

Data Index: 1215303 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.9775. Min Act: -0.0000

Data Index: 1632296 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.9858. Min Act: -0.0000

Data Index: 213566 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.8414. Min Act: -0.0000

Data Index: 9840 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.6503. Min Act: -0.0000

Data Index: 728495 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.7661. Min Act: -0.0000

Data Index: 859442 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.5674. Min Act: -0.0000

Data Index: 1619850 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.7205. Min Act: -0.0000

Data Index: 443748 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.6951. Min Act: -0.0000

Data Index: 987526 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.8369. Min Act: -0.0000

Data Index: 1841434 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.5199. Min Act: -0.0000

Data Index: 1162563 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.6286. Min Act: -0.0000

Data Index: 244316 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.9472. Min Act: -0.0000

Data Index: 1868586 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.4428. Min Act: -0.0000

Data Index: 1461425 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 5.4906. Min Range: -5.4906

Max Act: 3.5702. Min Act: -0.0000

Data Index: 1051193 (The Pile)

Max Activating Token Index: 117