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

Dataset: The Pile

Neuron 222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1563435 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1547. Min Act: -0.0000

Data Index: 631947 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1146099 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1551217 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1471. Min Act: -0.0000

Data Index: 632152 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1267995 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1341. Min Act: -0.0000

Data Index: 279087 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1290. Min Act: -0.0000

Data Index: 616155 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1271. Min Act: -0.0000

Data Index: 37478 (The Pile)

Max Activating Token Index: 189

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1345522 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1732060 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1896359 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1277. Min Act: -0.0000

Data Index: 455031 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1501176 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1730904 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1688393 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1271. Min Act: -0.0000

Data Index: 125761 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1310685 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1962012 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1191. Min Act: -0.0000

Data Index: 968767 (The Pile)

Max Activating Token Index: 332