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

Dataset: The Pile

Neuron 2636 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: 1.2182. Min Range: -1.2182

Max Act: 1.0787. Min Act: -0.0000

Data Index: 214462 (The Pile)

Max Activating Token Index: 233

Text #1

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.2182. Min Act: -0.0000

Data Index: 41539 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1917460 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.2182. Min Range: -1.2182

Max Act: 1.0488. Min Act: -0.0000

Data Index: 363112 (The Pile)

Max Activating Token Index: 579

Text #4

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9254. Min Act: -0.0000

Data Index: 241646 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1262385 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1376345 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9439. Min Act: -0.0000

Data Index: 621034 (The Pile)

Max Activating Token Index: 868

Text #8

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9245. Min Act: -0.0000

Data Index: 982158 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9254. Min Act: -0.0000

Data Index: 307713 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9393. Min Act: -0.0000

Data Index: 421011 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8830. Min Act: -0.0000

Data Index: 266418 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8524. Min Act: -0.0000

Data Index: 246665 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1983021 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1907354 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.9003. Min Act: -0.0000

Data Index: 1331186 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1535071 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1763749 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8276. Min Act: -0.0000

Data Index: 681053 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.2182. Min Range: -1.2182

Max Act: 0.8993. Min Act: -0.0000

Data Index: 999454 (The Pile)

Max Activating Token Index: 914