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

Dataset: The Pile

Neuron 2705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7528. Min Act: -0.0000

Data Index: 161070 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7832. Min Act: -0.0000

Data Index: 831124 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.7622. Min Act: -0.0000

Data Index: 331044 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6924. Min Act: -0.0000

Data Index: 442210 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6634. Min Act: -0.0000

Data Index: 683611 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6682. Min Act: -0.0000

Data Index: 321690 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1412062 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1104593 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1535659 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5087. Min Act: -0.0000

Data Index: 405712 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1680350 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6148. Min Act: -0.0000

Data Index: 747816 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5983. Min Act: -0.0000

Data Index: 623158 (The Pile)

Max Activating Token Index: 531

Text #13

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5880. Min Act: -0.0000

Data Index: 745632 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.6191. Min Act: -0.0000

Data Index: 673639 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1934036 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5278. Min Act: -0.0000

Data Index: 763472 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1496382 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5942. Min Act: -0.0000

Data Index: 30974 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 0.7832. Min Range: -0.7832

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1652445 (The Pile)

Max Activating Token Index: 471