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

Dataset: The Pile

Neuron 2386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5936. Min Act: -0.0000

Data Index: 843741 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5959. Min Act: -0.0000

Data Index: 164598 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1013567 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1363708 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.6151. Min Act: -0.0000

Data Index: 123995 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5724. Min Act: -0.0000

Data Index: 60268 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5493. Min Act: -0.0000

Data Index: 131914 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5642. Min Act: -0.0000

Data Index: 600075 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1819503 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1205983 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5474. Min Act: -0.0000

Data Index: 215088 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1398012 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1051401 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1862116 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5394. Min Act: -0.0000

Data Index: 788531 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5527. Min Act: -0.0000

Data Index: 233471 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1239837 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1132441 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1126798 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.6151. Min Range: -0.6151

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1596522 (The Pile)

Max Activating Token Index: 313