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

Dataset: The Pile

Neuron 205 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1473840 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7838. Min Act: -0.0000

Data Index: 264240 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.8429. Min Act: -0.0000

Data Index: 494762 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.8408. Min Act: -0.0000

Data Index: 290860 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7361. Min Act: -0.0000

Data Index: 675095 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1343606 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1259097 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1573360 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1584952 (The Pile)

Max Activating Token Index: 600

Text #9

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1342691 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1001457 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6363. Min Act: -0.0000

Data Index: 507919 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6287. Min Act: 0.0000

Data Index: 1493834 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1957863 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1900143 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1850654 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6601. Min Act: -0.0000

Data Index: 720197 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6873. Min Act: -0.0000

Data Index: 850530 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6379. Min Act: -0.0000

Data Index: 512864 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.9024. Min Range: -0.9024

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1260012 (The Pile)

Max Activating Token Index: 849