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

Dataset: The Pile

Neuron 2585 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.9173. Min Act: -0.0000

Data Index: 1891048 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1576258 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.5171. Min Act: -0.0000

Data Index: 227958 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1332126 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1620229 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1688081 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1593456 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1555134 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.0348. Min Act: -0.0000

Data Index: 954278 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1098039 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1530414 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1289. Min Act: -0.0000

Data Index: 828603 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1473281 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1078. Min Act: -0.0000

Data Index: 1388791 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1508. Min Act: -0.0000

Data Index: 288161 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.0705. Min Act: -0.0000

Data Index: 247728 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.9173. Min Range: -1.9173

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1239462 (The Pile)

Max Activating Token Index: 665

Text #17

Max Range: 1.9173. Min Range: -1.9173

Max Act: 0.9084. Min Act: -0.0000

Data Index: 284542 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 1.9173. Min Range: -1.9173

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1554731 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 1.9173. Min Range: -1.9173

Max Act: 0.8934. Min Act: -0.0000

Data Index: 76607 (The Pile)

Max Activating Token Index: 658