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

Dataset: The Pile

Neuron 2706 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: 1.6403. Min Range: -1.6403

Max Act: 1.4861. Min Act: -0.0000

Data Index: 282652 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1260943 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1463401 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1719058 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1317833 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1270720 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1766. Min Act: -0.0000

Data Index: 694049 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1689740 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1660607 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1103706 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1106010 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1804512 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1615097 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1300. Min Act: -0.0000

Data Index: 911134 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1294968 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1208528 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1640. Min Act: -0.0000

Data Index: 585348 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1792049 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1844173 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 1.6403. Min Range: -1.6403

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1392831 (The Pile)

Max Activating Token Index: 137