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

Dataset: The Pile

Neuron 3005 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: 0.7373. Min Range: -0.7373

Max Act: 0.7373. Min Act: -0.0001

Data Index: 337834 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5385. Min Act: -0.0000

Data Index: 481950 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1338555 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1449082 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6051. Min Act: -0.0000

Data Index: 629826 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1795531 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5187. Min Act: -0.0000

Data Index: 445989 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4582. Min Act: -0.0000

Data Index: 418325 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1500937 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5367. Min Act: -0.0000

Data Index: 99636 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5365. Min Act: -0.0000

Data Index: 872596 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1029044 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1826053 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1334382 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1335229 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1870995 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4268. Min Act: -0.0000

Data Index: 799275 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6052. Min Act: -0.0000

Data Index: 758611 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1174635 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1254617 (The Pile)

Max Activating Token Index: 476