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

Dataset: The Pile

Neuron 4849 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: 1.0523. Min Range: -1.0523

Max Act: 1.0523. Min Act: -0.0000

Data Index: 424271 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.9294. Min Act: -0.0000

Data Index: 984189 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.9907. Min Act: -0.0000

Data Index: 754074 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1805231 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1626078 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.9608. Min Act: -0.0000

Data Index: 740919 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.9451. Min Act: -0.0000

Data Index: 622971 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1555652 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1601669 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1169830 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1564923 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8140. Min Act: -0.0000

Data Index: 320153 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1587369 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1537020 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1747016 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.7505. Min Act: -0.0000

Data Index: 351500 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1271703 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8228. Min Act: -0.0000

Data Index: 905192 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1108167 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.0523. Min Range: -1.0523

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1874994 (The Pile)

Max Activating Token Index: 36