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

Dataset: The Pile

Neuron 2630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1662111 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1148672 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8633. Min Act: -0.0000

Data Index: 941320 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9594. Min Act: -0.0000

Data Index: 88430 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8584. Min Act: -0.0000

Data Index: 122156 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1305154 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1089109 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8317. Min Act: -0.0000

Data Index: 1350288 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1492942 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9422. Min Act: -0.0000

Data Index: 374114 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7946. Min Act: -0.0000

Data Index: 404346 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7894. Min Act: -0.0000

Data Index: 884576 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1407474 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7294. Min Act: -0.0000

Data Index: 394019 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7391. Min Act: -0.0000

Data Index: 974972 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7379. Min Act: -0.0000

Data Index: 129861 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1157509 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7757. Min Act: -0.0000

Data Index: 380912 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1359422 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1435688 (The Pile)

Max Activating Token Index: 258