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

Dataset: The Pile

Neuron 1944 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: 1.3230. Min Range: -1.3230

Max Act: 1.3230. Min Act: -0.0000

Data Index: 1636034 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1510512 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1977520 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1552213 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.0949. Min Act: -0.0000

Data Index: 278480 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1164220 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9650. Min Act: -0.0000

Data Index: 419675 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.0372. Min Act: -0.0000

Data Index: 489209 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.3230. Min Range: -1.3230

Max Act: 1.0412. Min Act: -0.0000

Data Index: 95422 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9539. Min Act: -0.0000

Data Index: 142217 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1513736 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1978822 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1935789 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1822422 (The Pile)

Max Activating Token Index: 916

Text #14

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1257006 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9875. Min Act: -0.0000

Data Index: 1284426 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1368173 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1380387 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1238885 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 1.3230. Min Range: -1.3230

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1438273 (The Pile)

Max Activating Token Index: 157