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

Dataset: The Pile

Neuron 194 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: 1.5162. Min Range: -1.5162

Max Act: 1.5162. Min Act: -0.0000

Data Index: 1795902 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1301743 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1371919 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.2813. Min Act: -0.0000

Data Index: 575457 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.3201. Min Act: -0.0000

Data Index: 505935 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1476518 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1172668 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1773246 (The Pile)

Max Activating Token Index: 758

Text #8

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1077998 (The Pile)

Max Activating Token Index: 308

Text #9

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.1735. Min Act: -0.0000

Data Index: 828053 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0589. Min Act: -0.0000

Data Index: 923939 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1170164 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.2126. Min Act: -0.0000

Data Index: 336788 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1287269 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1103692 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 1.5162. Min Range: -1.5162

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1661976 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.1482. Min Act: -0.0000

Data Index: 84058 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1646266 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 1.5162. Min Range: -1.5162

Max Act: 1.0419. Min Act: -0.0000

Data Index: 140512 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.5162. Min Range: -1.5162

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1749206 (The Pile)

Max Activating Token Index: 974