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

Dataset: The Pile

Neuron 1228 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: 0.4308. Min Range: -0.4308

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1400274 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4040. Min Act: -0.0000

Data Index: 254289 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1227089 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1511258 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1328750 (The Pile)

Max Activating Token Index: 652

Text #5

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1401680 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1608494 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3184. Min Act: -0.0000

Data Index: 635679 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3274. Min Act: -0.0000

Data Index: 223302 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1456328 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1690062 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3026. Min Act: -0.0000

Data Index: 500295 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2733. Min Act: -0.0000

Data Index: 151432 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1937751 (The Pile)

Max Activating Token Index: 476

Text #14

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1118746 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2960. Min Act: -0.0000

Data Index: 303343 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2755. Min Act: -0.0000

Data Index: 270064 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1084648 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2822. Min Act: -0.0000

Data Index: 900166 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1051623 (The Pile)

Max Activating Token Index: 145