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

Dataset: The Pile

Neuron 2096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2889. Min Act: -0.0000

Data Index: 439639 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1974453 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1615. Min Act: -0.0000

Data Index: 474511 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1599. Min Act: -0.0000

Data Index: 557115 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1637. Min Act: -0.0000

Data Index: 239968 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1346194 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1413172 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1448405 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1086418 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1300. Min Act: -0.0000

Data Index: 1385725 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1624410 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1749199 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1269. Min Act: -0.0000

Data Index: 147833 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1347. Min Act: -0.0000

Data Index: 463242 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1554520 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1238. Min Act: -0.0000

Data Index: 175565 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1967632 (The Pile)

Max Activating Token Index: 947

Text #17

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1101. Min Act: -0.0000

Data Index: 980965 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1199. Min Act: -0.0000

Data Index: 1117329 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.2889. Min Range: -0.2889

Max Act: 0.1207. Min Act: -0.0000

Data Index: 673571 (The Pile)

Max Activating Token Index: 902