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

Dataset: The Pile

Neuron 117 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: 0.9366. Min Range: -0.9366

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1410215 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1935609 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1167841 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1232302 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1720146 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1747736 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1407748 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7241. Min Act: -0.0000

Data Index: 389354 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6944. Min Act: -0.0000

Data Index: 786626 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6867. Min Act: -0.0000

Data Index: 30699 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6911. Min Act: -0.0000

Data Index: 837609 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1390949 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7310. Min Act: -0.0000

Data Index: 316301 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1826833 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6787. Min Act: -0.0000

Data Index: 197730 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6981. Min Act: -0.0000

Data Index: 142648 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6524. Min Act: -0.0000

Data Index: 795696 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1262118 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6661. Min Act: -0.0000

Data Index: 44053 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1933645 (The Pile)

Max Activating Token Index: 480