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

Dataset: The Pile

Neuron 649 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1775865 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.1091. Min Act: -0.0000

Data Index: 491398 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1337295 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9710. Min Act: -0.0000

Data Index: 348637 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.1091. Min Range: -1.1091

Max Act: 1.0705. Min Act: -0.0000

Data Index: 73264 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1163289 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1868844 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1114863 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1309406 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8659. Min Act: -0.0000

Data Index: 776122 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8681. Min Act: -0.0000

Data Index: 295281 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1113493 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1051983 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8576. Min Act: -0.0000

Data Index: 964377 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8056. Min Act: -0.0000

Data Index: 177782 (The Pile)

Max Activating Token Index: 509

Text #15

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1927624 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1701567 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1192182 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8329. Min Act: -0.0000

Data Index: 24225 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.1091. Min Range: -1.1091

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1043977 (The Pile)

Max Activating Token Index: 867