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

Dataset: The Pile

Neuron 582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.7703. Min Act: -0.0000

Data Index: 1530619 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.7703. Min Act: -0.0000

Data Index: 1386403 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.3478. Min Act: -0.0000

Data Index: 1957051 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.3070. Min Act: 0.0000

Data Index: 1340626 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.3761. Min Act: -0.0000

Data Index: 915070 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.2584. Min Act: -0.0000

Data Index: 108389 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.3685. Min Act: -0.0000

Data Index: 552795 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.2000. Min Act: -0.0000

Data Index: 1245573 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.2207. Min Act: -0.0000

Data Index: 387307 (The Pile)

Max Activating Token Index: 237

Text #9

Max Range: 5.7703. Min Range: -5.7703

Max Act: 4.9545. Min Act: -0.0000

Data Index: 1494373 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.1676. Min Act: -0.0000

Data Index: 1540473 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 5.7703. Min Range: -5.7703

Max Act: 4.8933. Min Act: -0.0000

Data Index: 905999 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.1114. Min Act: -0.0000

Data Index: 1812660 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.0781. Min Act: -0.0000

Data Index: 1629215 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.2556. Min Act: -0.0000

Data Index: 141247 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 5.7703. Min Range: -5.7703

Max Act: 4.9774. Min Act: -0.0000

Data Index: 1722927 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.0232. Min Act: -0.0000

Data Index: 1995717 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 5.7703. Min Range: -5.7703

Max Act: 4.7854. Min Act: -0.0000

Data Index: 1229998 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 5.7703. Min Range: -5.7703

Max Act: 4.9497. Min Act: -0.0000

Data Index: 628072 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 5.7703. Min Range: -5.7703

Max Act: 5.1442. Min Act: -0.0000

Data Index: 310961 (The Pile)

Max Activating Token Index: 3