Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1335 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4042. Min Act: -0.0000

Data Index: 505205 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1737098 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1336585 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1363658 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1187044 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3487. Min Act: -0.0000

Data Index: 928974 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1503023 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3298. Min Act: -0.0000

Data Index: 924798 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3276. Min Act: -0.0000

Data Index: 38282 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2921. Min Act: -0.0000

Data Index: 243150 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1467200 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2879. Min Act: -0.0000

Data Index: 345522 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1646368 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1692192 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1903886 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2833. Min Act: -0.0000

Data Index: 97682 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2863. Min Act: -0.0000

Data Index: 604934 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1618214 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1923558 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2850. Min Act: -0.0000

Data Index: 881349 (The Pile)

Max Activating Token Index: 758