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

Dataset: The Pile

Neuron 3220 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: 1.9162. Min Range: -1.9162

Max Act: 1.9162. Min Act: -0.0000

Data Index: 848478 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.8640. Min Act: -0.0000

Data Index: 311071 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.8035. Min Act: -0.0000

Data Index: 910682 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.7876. Min Act: -0.0000

Data Index: 466821 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.7852. Min Act: -0.0000

Data Index: 111737 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.7876. Min Act: -0.0000

Data Index: 1986712 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5127. Min Act: -0.0000

Data Index: 836180 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1084969 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6924. Min Act: -0.0000

Data Index: 1800314 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1731528 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1335169 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1501693 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1418710 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.6020. Min Act: -0.0000

Data Index: 853660 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5130. Min Act: -0.0000

Data Index: 1413840 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1274130 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4199. Min Act: -0.0000

Data Index: 718380 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.3375. Min Act: -0.0000

Data Index: 452780 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1978176 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 1.9162. Min Range: -1.9162

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1844402 (The Pile)

Max Activating Token Index: 758