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

Dataset: The Pile

Neuron 636 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1875. Min Act: -0.0000

Data Index: 613075 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1451322 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.3670. Min Act: -0.0000

Data Index: 179541 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1651846 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1445103 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.4413. Min Act: 0.0001

Data Index: 474703 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1691. Min Act: -0.0000

Data Index: 74337 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1267. Min Act: 0.0000

Data Index: 1729243 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.1462. Min Act: -0.0000

Data Index: 858600 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2549. Min Act: 0.0000

Data Index: 320202 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1498841 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 1.5224. Min Range: -1.5224

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1478652 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0875. Min Act: 0.0001

Data Index: 1798459 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0770. Min Act: -0.0000

Data Index: 765880 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1379388 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0264. Min Act: -0.0000

Data Index: 111726 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1363958 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0071. Min Act: -0.0000

Data Index: 915836 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1027996 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 1.5224. Min Range: -1.5224

Max Act: 1.0385. Min Act: 0.0000

Data Index: 1375438 (The Pile)

Max Activating Token Index: 335