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

Dataset: The Pile

Neuron 2865 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: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0000

Data Index: 753871 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1035742 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1755057 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1260052 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1318533 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1398. Min Act: -0.0000

Data Index: 711749 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1439. Min Act: -0.0000

Data Index: 728230 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1486. Min Act: -0.0000

Data Index: 325724 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1412. Min Act: -0.0000

Data Index: 278140 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1410739 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1365. Min Act: -0.0000

Data Index: 215497 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1926424 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1422. Min Act: -0.0000

Data Index: 54786 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1401691 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1551176 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1258. Min Act: -0.0000

Data Index: 946107 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1806494 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1071300 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1313. Min Act: -0.0000

Data Index: 955128 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1250. Min Act: -0.0000

Data Index: 557198 (The Pile)

Max Activating Token Index: 404