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

Dataset: The Pile

Neuron 585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.3262. Min Act: -0.0000

Data Index: 916485 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.0781. Min Act: -0.0000

Data Index: 201306 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.3262. Min Range: -1.3262

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1620400 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.9573. Min Act: -0.0000

Data Index: 972076 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.6669. Min Act: -0.0000

Data Index: 23244 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.7184. Min Act: -0.0000

Data Index: 575040 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5712. Min Act: -0.0000

Data Index: 279955 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1676597 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1756638 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1640206 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5497. Min Act: -0.0000

Data Index: 831008 (The Pile)

Max Activating Token Index: 482

Text #11

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1554606 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5095. Min Act: -0.0000

Data Index: 967615 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.4946. Min Act: -0.0000

Data Index: 877474 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5123. Min Act: -0.0000

Data Index: 316030 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5083. Min Act: -0.0000

Data Index: 543005 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.4929. Min Act: -0.0000

Data Index: 228497 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1869322 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.4789. Min Act: -0.0000

Data Index: 371037 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 1.3262. Min Range: -1.3262

Max Act: 0.5139. Min Act: -0.0000

Data Index: 609994 (The Pile)

Max Activating Token Index: 724