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

Dataset: The Pile

Neuron 872 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: 3.2909. Min Range: -3.2909

Max Act: 3.1461. Min Act: -0.0000

Data Index: 49742 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 3.2909. Min Range: -3.2909

Max Act: 3.2909. Min Act: -0.0000

Data Index: 1638140 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 3.2909. Min Range: -3.2909

Max Act: 3.1576. Min Act: -0.0000

Data Index: 1039350 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8249. Min Act: -0.0000

Data Index: 1293091 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 3.2909. Min Range: -3.2909

Max Act: 3.1829. Min Act: -0.0000

Data Index: 202446 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8421. Min Act: -0.0000

Data Index: 196525 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 3.2909. Min Range: -3.2909

Max Act: 3.0929. Min Act: -0.0000

Data Index: 705403 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.7990. Min Act: -0.0000

Data Index: 1612954 (The Pile)

Max Activating Token Index: 224

Text #8

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8653. Min Act: -0.0000

Data Index: 1706807 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.5140. Min Act: -0.0000

Data Index: 393401 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8682. Min Act: -0.0000

Data Index: 1280622 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8042. Min Act: -0.0000

Data Index: 1953093 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8361. Min Act: -0.0000

Data Index: 1829305 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.6753. Min Act: -0.0000

Data Index: 1396166 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.4898. Min Act: -0.0000

Data Index: 1565016 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.6376. Min Act: -0.0000

Data Index: 153622 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.5958. Min Act: -0.0000

Data Index: 1321981 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.7793. Min Act: -0.0000

Data Index: 952435 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.8289. Min Act: -0.0000

Data Index: 108667 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 3.2909. Min Range: -3.2909

Max Act: 2.7305. Min Act: -0.0000

Data Index: 1922806 (The Pile)

Max Activating Token Index: 257