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

Dataset: The Pile

Neuron 598 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: 1.6477. Min Range: -1.6477

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1578958 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5102. Min Act: -0.0000

Data Index: 570951 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.4862. Min Act: -0.0000

Data Index: 908799 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1985814 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6477. Min Act: -0.0000

Data Index: 1338036 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3769. Min Act: -0.0000

Data Index: 485561 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1345446 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.4277. Min Act: -0.0000

Data Index: 880180 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1116604 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3253. Min Act: -0.0000

Data Index: 1527393 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1184687 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1914811 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3165. Min Act: -0.0000

Data Index: 236500 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3905. Min Act: -0.0000

Data Index: 833950 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.2898. Min Act: -0.0000

Data Index: 635012 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3165. Min Act: -0.0000

Data Index: 688829 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3984. Min Act: -0.0000

Data Index: 595949 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1473128 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.3213. Min Act: -0.0000

Data Index: 608102 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.2741. Min Act: -0.0000

Data Index: 696631 (The Pile)

Max Activating Token Index: 343