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

Dataset: The Pile

Neuron 378 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.3275. Min Act: -0.0000

Data Index: 564742 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.0490. Min Act: -0.0000

Data Index: 1940027 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.3211. Min Act: -0.0000

Data Index: 144972 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.1473. Min Act: -0.0000

Data Index: 980334 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.6040. Min Act: -0.0000

Data Index: 35645 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.2802. Min Act: -0.0000

Data Index: 413167 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.0555. Min Act: -0.0000

Data Index: 1850079 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.0968. Min Act: -0.0000

Data Index: 102001 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.9049. Min Act: -0.0000

Data Index: 132975 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 5.3275. Min Range: -5.3275

Max Act: 5.0558. Min Act: -0.0000

Data Index: 588278 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.6951. Min Act: -0.0000

Data Index: 58010 (The Pile)

Max Activating Token Index: 511

Text #11

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.8550. Min Act: -0.0000

Data Index: 407734 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.9892. Min Act: -0.0000

Data Index: 1607605 (The Pile)

Max Activating Token Index: 502

Text #13

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.8447. Min Act: -0.0000

Data Index: 718151 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.4116. Min Act: -0.0000

Data Index: 1084633 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.7331. Min Act: -0.0000

Data Index: 439450 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.7323. Min Act: -0.0000

Data Index: 1278255 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.6791. Min Act: -0.0000

Data Index: 1712293 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.7041. Min Act: -0.0000

Data Index: 112276 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 5.3275. Min Range: -5.3275

Max Act: 4.6946. Min Act: -0.0000

Data Index: 1509150 (The Pile)

Max Activating Token Index: 138