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

Dataset: The Pile

Neuron 4066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.7498. Min Act: -0.0000

Data Index: 487414 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6106. Min Act: -0.0000

Data Index: 772971 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.6872. Min Act: -0.0000

Data Index: 784064 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1642888 (The Pile)

Max Activating Token Index: 566

Text #4

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.5124. Min Act: -0.0000

Data Index: 568991 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1269873 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1682350 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1678. Min Act: -0.0000

Data Index: 867774 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.2806. Min Act: -0.0000

Data Index: 239791 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1598. Min Act: -0.0000

Data Index: 943288 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.2624. Min Act: 0.0000

Data Index: 916288 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1363892 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1021630 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1681. Min Act: -0.0000

Data Index: 494960 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1708. Min Act: -0.0000

Data Index: 977209 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1543893 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.2909. Min Act: -0.0000

Data Index: 98720 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1098. Min Act: -0.0000

Data Index: 203578 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.1900. Min Act: -0.0000

Data Index: 993784 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.7498. Min Range: -1.7498

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1493112 (The Pile)

Max Activating Token Index: 712