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

Dataset: The Pile

Neuron 1181 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: 1.5453. Min Range: -1.5453

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1868145 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1669489 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2809. Min Act: -0.0000

Data Index: 44491 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1395033 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2042. Min Act: -0.0000

Data Index: 343434 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1326. Min Act: -0.0000

Data Index: 983331 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1377252 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1225770 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1813770 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0349. Min Act: -0.0000

Data Index: 613864 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0330. Min Act: -0.0000

Data Index: 731586 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1785946 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0693. Min Act: -0.0000

Data Index: 1408434 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1823035 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1306407 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1195611 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9607. Min Act: -0.0000

Data Index: 1496047 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9908. Min Act: -0.0000

Data Index: 516817 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9594. Min Act: -0.0000

Data Index: 301756 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 1.5453. Min Range: -1.5453

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1177658 (The Pile)

Max Activating Token Index: 270