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

Dataset: The Pile

Neuron 2588 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: 1.5263. Min Range: -1.5263

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1274855 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1502525 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.5263. Min Act: -0.0000

Data Index: 468963 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1373692 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1092449 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2680. Min Act: -0.0000

Data Index: 1477088 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0847. Min Act: -0.0000

Data Index: 852843 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1686221 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1637997 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1743469 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0761. Min Act: -0.0000

Data Index: 463915 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2806. Min Act: -0.0000

Data Index: 1059348 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1517577 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1343094 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.2048. Min Act: -0.0000

Data Index: 133115 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1758082 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1282. Min Act: -0.0000

Data Index: 733074 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1355721 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1206472 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 1.5263. Min Range: -1.5263

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1313914 (The Pile)

Max Activating Token Index: 700