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

Dataset: The Pile

Neuron 2008 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: 0.8554. Min Range: -0.8554

Max Act: 0.8554. Min Act: -0.0000

Data Index: 670706 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1187599 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7214. Min Act: -0.0000

Data Index: 994511 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7248. Min Act: -0.0000

Data Index: 850581 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1054109 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7166. Min Act: -0.0000

Data Index: 747813 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1550303 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1173438 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7572. Min Act: -0.0000

Data Index: 50017 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1439562 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7164. Min Act: -0.0000

Data Index: 867731 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7325. Min Act: -0.0000

Data Index: 732187 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1468660 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7054. Min Act: -0.0000

Data Index: 660304 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1752812 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6981. Min Act: -0.0000

Data Index: 866489 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1479688 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1555675 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.6961. Min Act: -0.0000

Data Index: 752010 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.8554. Min Range: -0.8554

Max Act: 0.7311. Min Act: -0.0000

Data Index: 891063 (The Pile)

Max Activating Token Index: 1005