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

Dataset: The Pile

Neuron 4313 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: 3.5051. Min Range: -3.5051

Max Act: 3.5051. Min Act: -0.0000

Data Index: 828463 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.4192. Min Act: -0.0000

Data Index: 1065995 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.3130. Min Act: -0.0000

Data Index: 1834599 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.0185. Min Act: -0.0000

Data Index: 694303 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.0905. Min Act: -0.0000

Data Index: 545460 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.3542. Min Act: -0.0000

Data Index: 982690 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.8137. Min Act: -0.0000

Data Index: 1808492 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.1701. Min Act: -0.0000

Data Index: 1733929 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.1388. Min Act: -0.0000

Data Index: 675366 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.0036. Min Act: -0.0000

Data Index: 1822036 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.8355. Min Act: -0.0000

Data Index: 763043 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.0993. Min Act: -0.0000

Data Index: 722093 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.9478. Min Act: -0.0000

Data Index: 311238 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.7927. Min Act: -0.0000

Data Index: 1410707 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.9382. Min Act: -0.0000

Data Index: 840781 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.9145. Min Act: -0.0000

Data Index: 985280 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.8891. Min Act: -0.0000

Data Index: 1913839 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.9100. Min Act: -0.0000

Data Index: 1658891 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 3.5051. Min Range: -3.5051

Max Act: 3.0386. Min Act: -0.0000

Data Index: 1399543 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 3.5051. Min Range: -3.5051

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1549448 (The Pile)

Max Activating Token Index: 561