Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2314 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.5265. Min Act: -0.0000

Data Index: 399547 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4304. Min Act: -0.0000

Data Index: 140603 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.4446. Min Act: -0.0000

Data Index: 492943 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3301. Min Act: -0.0000

Data Index: 716977 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3511. Min Act: -0.0000

Data Index: 498229 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3267. Min Act: -0.0000

Data Index: 614648 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2470. Min Act: -0.0000

Data Index: 958961 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2788. Min Act: -0.0000

Data Index: 248342 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1065125 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2676. Min Act: -0.0000

Data Index: 516773 (The Pile)

Max Activating Token Index: 237

Text #10

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1991652 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2999. Min Act: -0.0000

Data Index: 652694 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1925166 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2668. Min Act: -0.0000

Data Index: 362235 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1414406 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2687. Min Act: -0.0000

Data Index: 31956 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1515503 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2770. Min Act: -0.0000

Data Index: 242606 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1452931 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.5265. Min Range: -0.5265

Max Act: 0.2801. Min Act: -0.0000

Data Index: 772850 (The Pile)

Max Activating Token Index: 733