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

Dataset: The Pile

Neuron 3031 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: 1.2498. Min Range: -1.2498

Max Act: 1.2498. Min Act: -0.0000

Data Index: 49145 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 1.2498. Min Range: -1.2498

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1397998 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1442259 (The Pile)

Max Activating Token Index: 932

Text #3

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1779501 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1418501 (The Pile)

Max Activating Token Index: 863

Text #5

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8586. Min Act: -0.0000

Data Index: 768581 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7808. Min Act: -0.0000

Data Index: 278749 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.6645. Min Act: -0.0000

Data Index: 461404 (The Pile)

Max Activating Token Index: 740

Text #8

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7232. Min Act: -0.0000

Data Index: 404208 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7455. Min Act: -0.0000

Data Index: 703648 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1242833 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1093731 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1206360 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1217098 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7484. Min Act: -0.0000

Data Index: 437423 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1719082 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1345346 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7278. Min Act: -0.0000

Data Index: 201272 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1028521 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 1.2498. Min Range: -1.2498

Max Act: 0.7160. Min Act: -0.0000

Data Index: 665523 (The Pile)

Max Activating Token Index: 832