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

Dataset: The Pile

Neuron 1672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1469606 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5027. Min Act: -0.0000

Data Index: 180333 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5528. Min Act: -0.0000

Data Index: 854854 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5538. Min Act: -0.0000

Data Index: 934125 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4164. Min Act: -0.0000

Data Index: 360029 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4373. Min Act: -0.0000

Data Index: 456181 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4602. Min Act: -0.0000

Data Index: 366686 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1675267 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5211. Min Act: -0.0000

Data Index: 1575186 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3449. Min Act: -0.0000

Data Index: 211737 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3194. Min Act: -0.0000

Data Index: 1581184 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1452705 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1286687 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3055. Min Act: -0.0000

Data Index: 153957 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3633. Min Act: -0.0000

Data Index: 286849 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2010. Min Act: -0.0000

Data Index: 546968 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.1916. Min Act: -0.0000

Data Index: 555206 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1667215 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1808254 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3306. Min Act: -0.0000

Data Index: 672793 (The Pile)

Max Activating Token Index: 574