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

Dataset: The Pile

Neuron 4012 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: 1.4689. Min Range: -1.4689

Max Act: 1.4689. Min Act: -0.0000

Data Index: 36008 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1170816 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1297991 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.1146. Min Act: -0.0000

Data Index: 956427 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.1875. Min Act: -0.0000

Data Index: 890271 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.1721. Min Act: -0.0000

Data Index: 542121 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.4689. Min Range: -1.4689

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1907405 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1706643 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1180488 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.9625. Min Act: -0.0000

Data Index: 893813 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.9073. Min Act: -0.0000

Data Index: 304624 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1757883 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8305. Min Act: -0.0000

Data Index: 534206 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1151227 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1209171 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1954138 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.7969. Min Act: -0.0000

Data Index: 666301 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8157. Min Act: -0.0000

Data Index: 93581 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.7903. Min Act: -0.0000

Data Index: 769958 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 1.4689. Min Range: -1.4689

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1480586 (The Pile)

Max Activating Token Index: 289