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

Dataset: The Pile

Neuron 1326 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: 5.1557. Min Range: -5.1557

Max Act: 5.1557. Min Act: -0.0000

Data Index: 1856358 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.2632. Min Act: -0.0000

Data Index: 564389 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.4020. Min Act: -0.0000

Data Index: 1372757 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.5938. Min Act: -0.0000

Data Index: 1366340 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.0818. Min Act: -0.0000

Data Index: 103036 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.1803. Min Act: -0.0000

Data Index: 136245 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 5.1557. Min Range: -5.1557

Max Act: 4.0084. Min Act: -0.0000

Data Index: 1153561 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.8767. Min Act: -0.0000

Data Index: 1916311 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.9330. Min Act: -0.0000

Data Index: 1637409 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.4153. Min Act: -0.0000

Data Index: 1819518 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.9005. Min Act: -0.0000

Data Index: 507343 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.5634. Min Act: -0.0000

Data Index: 189068 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.7249. Min Act: -0.0000

Data Index: 520082 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.8836. Min Act: -0.0000

Data Index: 730854 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.6933. Min Act: -0.0000

Data Index: 1160142 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.6740. Min Act: -0.0000

Data Index: 70375 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.5932. Min Act: -0.0000

Data Index: 323079 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.5773. Min Act: -0.0000

Data Index: 110818 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.6586. Min Act: -0.0000

Data Index: 42704 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 5.1557. Min Range: -5.1557

Max Act: 3.7492. Min Act: -0.0000

Data Index: 248275 (The Pile)

Max Activating Token Index: 815