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

Dataset: The Pile

Neuron 3184 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: 0.3933. Min Range: -0.3933

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1381006 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1167034 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3474. Min Act: -0.0000

Data Index: 292119 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1829551 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3285. Min Act: -0.0000

Data Index: 751663 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2828. Min Act: -0.0000

Data Index: 927333 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3024. Min Act: -0.0000

Data Index: 727069 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1919344 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1179289 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1172868 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2761. Min Act: -0.0000

Data Index: 898135 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1076552 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3002. Min Act: -0.0000

Data Index: 414239 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2941. Min Act: -0.0000

Data Index: 707043 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1631299 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1578100 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1718222 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2727. Min Act: -0.0000

Data Index: 206040 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2695. Min Act: -0.0000

Data Index: 753840 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2577. Min Act: -0.0000

Data Index: 914292 (The Pile)

Max Activating Token Index: 370