Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.1748. Min Range: -3.1748

Max Act: 3.1748. Min Act: -0.0000

Data Index: 1239684 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.8428. Min Act: -0.0000

Data Index: 1045767 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.8991. Min Act: -0.0000

Data Index: 983880 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.9956. Min Act: -0.0000

Data Index: 61486 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.4879. Min Act: -0.0000

Data Index: 889310 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.5759. Min Act: -0.0000

Data Index: 1506939 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.3923. Min Act: -0.0001

Data Index: 155423 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.7322. Min Act: -0.0000

Data Index: 865113 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.1964. Min Act: -0.0000

Data Index: 1329922 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 3.1748. Min Range: -3.1748

Max Act: 1.9951. Min Act: -0.0000

Data Index: 487272 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.2933. Min Act: -0.0000

Data Index: 597542 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.0634. Min Act: -0.0000

Data Index: 193888 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.1437. Min Act: -0.0000

Data Index: 379802 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.1878. Min Act: -0.0000

Data Index: 665259 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.0349. Min Act: -0.0000

Data Index: 879406 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 3.1748. Min Range: -3.1748

Max Act: 1.9305. Min Act: -0.0000

Data Index: 1158045 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 3.1748. Min Range: -3.1748

Max Act: 1.9738. Min Act: -0.0000

Data Index: 693740 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 3.1748. Min Range: -3.1748

Max Act: 1.8586. Min Act: -0.0000

Data Index: 907089 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 3.1748. Min Range: -3.1748

Max Act: 2.0429. Min Act: -0.0000

Data Index: 1685460 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 3.1748. Min Range: -3.1748

Max Act: 1.9112. Min Act: -0.0000

Data Index: 1827385 (The Pile)

Max Activating Token Index: 444