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

Dataset: The Pile

Neuron 4247 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: 0.7388. Min Range: -0.7388

Max Act: 0.7388. Min Act: 0.0000

Data Index: 66640 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1552901 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1527272 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1466605 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6582. Min Act: -0.0000

Data Index: 57163 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6365. Min Act: -0.0000

Data Index: 935794 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1315382 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6394. Min Act: -0.0000

Data Index: 749084 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6108. Min Act: -0.0000

Data Index: 457101 (The Pile)

Max Activating Token Index: 521

Text #9

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6139. Min Act: -0.0000

Data Index: 639702 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6059. Min Act: 0.0000

Data Index: 1780134 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1623752 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6001. Min Act: -0.0000

Data Index: 30835 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1643655 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5800. Min Act: 0.0000

Data Index: 500106 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1968009 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1594086 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1649118 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5596. Min Act: -0.0000

Data Index: 336945 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5523. Min Act: 0.0000

Data Index: 428767 (The Pile)

Max Activating Token Index: 527