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

Dataset: The Pile

Neuron 359 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: 4.4354. Min Range: -4.4354

Max Act: 4.4354. Min Act: -0.0000

Data Index: 786027 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.6653. Min Act: -0.0000

Data Index: 543984 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.4886. Min Act: -0.0000

Data Index: 1004864 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.3914. Min Act: 0.0000

Data Index: 151545 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.8159. Min Act: -0.0000

Data Index: 1285103 (The Pile)

Max Activating Token Index: 211

Text #5

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.6926. Min Act: -0.0000

Data Index: 539767 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.5893. Min Act: -0.0000

Data Index: 1565454 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.4062. Min Act: -0.0000

Data Index: 720315 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.5307. Min Act: -0.0000

Data Index: 218879 (The Pile)

Max Activating Token Index: 990

Text #9

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.4497. Min Act: -0.0000

Data Index: 792724 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.2011. Min Act: -0.0000

Data Index: 216489 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.3329. Min Act: -0.0000

Data Index: 1095955 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1176. Min Act: -0.0000

Data Index: 932895 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1180. Min Act: -0.0000

Data Index: 877947 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 4.4354. Min Range: -4.4354

Max Act: 2.8940. Min Act: -0.0000

Data Index: 406152 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1790. Min Act: -0.0000

Data Index: 1243248 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 4.4354. Min Range: -4.4354

Max Act: 2.9812. Min Act: -0.0000

Data Index: 59310 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1472. Min Act: -0.0000

Data Index: 1220878 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 4.4354. Min Range: -4.4354

Max Act: 3.1496. Min Act: -0.0000

Data Index: 1358927 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 4.4354. Min Range: -4.4354

Max Act: 2.9536. Min Act: -0.0000

Data Index: 390443 (The Pile)

Max Activating Token Index: 628