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

Dataset: The Pile

Neuron 59 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1327. Min Range: -3.1327

Max Act: 3.1327. Min Act: -0.0000

Data Index: 1054867 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 3.1327. Min Range: -3.1327

Max Act: 2.1062. Min Act: -0.0000

Data Index: 52656 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.7687. Min Act: -0.0000

Data Index: 837249 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.7593. Min Act: -0.0000

Data Index: 822486 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.7135. Min Act: -0.0000

Data Index: 1970527 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.4498. Min Act: -0.0000

Data Index: 811606 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5771. Min Act: -0.0000

Data Index: 967512 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.6001. Min Act: -0.0000

Data Index: 556845 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5713. Min Act: -0.0000

Data Index: 1174847 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5310. Min Act: -0.0000

Data Index: 371167 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1643628 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5734. Min Act: -0.0000

Data Index: 398581 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1855393 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1491040 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.4427. Min Act: -0.0000

Data Index: 471512 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.4394. Min Act: -0.0000

Data Index: 401865 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.4268. Min Act: -0.0000

Data Index: 803125 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.4241. Min Act: -0.0000

Data Index: 163077 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1185609 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 3.1327. Min Range: -3.1327

Max Act: 1.2950. Min Act: -0.0000

Data Index: 1795369 (The Pile)

Max Activating Token Index: 826