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

Dataset: The Pile

Neuron 1394 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: 1.3154. Min Range: -1.3154

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1434266 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1249727 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.1393. Min Act: -0.0000

Data Index: 1598339 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1404245 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1017498 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0533. Min Act: -0.0000

Data Index: 1689298 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0810. Min Act: -0.0000

Data Index: 542420 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0523. Min Act: -0.0000

Data Index: 284968 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1214660 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0645. Min Act: -0.0000

Data Index: 608172 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0371. Min Act: -0.0000

Data Index: 349587 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 1.3154. Min Range: -1.3154

Max Act: 1.0402. Min Act: -0.0000

Data Index: 948755 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9900. Min Act: -0.0000

Data Index: 132794 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9822. Min Act: -0.0000

Data Index: 985878 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1866685 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9536. Min Act: -0.0000

Data Index: 867007 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1300007 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1209916 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1064215 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 1.3154. Min Range: -1.3154

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1018430 (The Pile)

Max Activating Token Index: 458