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

Dataset: The Pile

Neuron 875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1887359 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.6140. Min Act: -0.0000

Data Index: 329344 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1515809 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1032125 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3908. Min Act: -0.0000

Data Index: 1237094 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1584123 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3612. Min Act: -0.0000

Data Index: 767735 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.5082. Min Act: -0.0000

Data Index: 925430 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1891458 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3997. Min Act: -0.0000

Data Index: 19061 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2035. Min Act: -0.0000

Data Index: 29478 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1554296 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1073053 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3064. Min Act: -0.0000

Data Index: 659979 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1275245 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1342227 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3068. Min Act: -0.0000

Data Index: 965304 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.1966. Min Act: -0.0000

Data Index: 966058 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3516. Min Act: -0.0000

Data Index: 638945 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.6527. Min Range: -1.6527

Max Act: 1.3250. Min Act: -0.0000

Data Index: 356922 (The Pile)

Max Activating Token Index: 392