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

Dataset: The Pile

Neuron 4776 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1222627 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1091369 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1537217 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1923541 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1598. Min Act: -0.0000

Data Index: 952405 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1096836 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1398. Min Act: -0.0000

Data Index: 541451 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1513. Min Act: -0.0000

Data Index: 990880 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1184655 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1478. Min Act: -0.0000

Data Index: 756702 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1652194 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1293. Min Act: -0.0000

Data Index: 133737 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1048133 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1339192 (The Pile)

Max Activating Token Index: 874

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1274. Min Act: -0.0000

Data Index: 697131 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1658491 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1316629 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1162. Min Act: -0.0000

Data Index: 598783 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1307. Min Act: -0.0000

Data Index: 205401 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1125. Min Act: -0.0000

Data Index: 397201 (The Pile)

Max Activating Token Index: 219