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

Dataset: The Pile

Neuron 2178 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: 0.2838. Min Range: -0.2838

Max Act: 0.2838. Min Act: -0.0000

Data Index: 318077 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1780. Min Act: -0.0000

Data Index: 553743 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1560. Min Act: -0.0000

Data Index: 797919 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1616. Min Act: -0.0000

Data Index: 800607 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1527. Min Act: -0.0000

Data Index: 146570 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1572. Min Act: -0.0000

Data Index: 860503 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1239684 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1935150 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1486. Min Act: -0.0000

Data Index: 259829 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1605. Min Act: -0.0000

Data Index: 984316 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1336. Min Act: -0.0000

Data Index: 1414647 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1460. Min Act: -0.0000

Data Index: 444744 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1451763 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1379. Min Act: -0.0000

Data Index: 379217 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1446. Min Act: -0.0000

Data Index: 548783 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1459. Min Act: -0.0000

Data Index: 367124 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1552405 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1414956 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1584. Min Act: -0.0000

Data Index: 218163 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.2838. Min Range: -0.2838

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1312486 (The Pile)

Max Activating Token Index: 919