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

Dataset: The Pile

Neuron 5057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1448. Min Range: -1.1448

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1323702 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 1.1448. Min Range: -1.1448

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1535913 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1322459 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 1.1448. Min Range: -1.1448

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1464332 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9730. Min Act: -0.0000

Data Index: 864059 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9547. Min Act: -0.0000

Data Index: 721588 (The Pile)

Max Activating Token Index: 277

Text #6

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8705. Min Act: -0.0000

Data Index: 951265 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8421. Min Act: -0.0000

Data Index: 335643 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9149. Min Act: -0.0000

Data Index: 554328 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8734. Min Act: -0.0000

Data Index: 578905 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1600549 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1180480 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1065992 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8889. Min Act: -0.0000

Data Index: 364977 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8368. Min Act: -0.0000

Data Index: 917356 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1686851 (The Pile)

Max Activating Token Index: 904

Text #16

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8519. Min Act: -0.0000

Data Index: 930687 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.8156. Min Act: -0.0000

Data Index: 712070 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.7308. Min Act: -0.0000

Data Index: 907212 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 1.1448. Min Range: -1.1448

Max Act: 0.9051. Min Act: -0.0000

Data Index: 317942 (The Pile)

Max Activating Token Index: 905