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

Dataset: The Pile

Neuron 2290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0514. Min Range: -4.0514

Max Act: 4.0514. Min Act: -0.0000

Data Index: 224879 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.5646. Min Act: -0.0000

Data Index: 1540540 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.1355. Min Act: -0.0000

Data Index: 878903 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.2610. Min Act: -0.0000

Data Index: 1126155 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.5514. Min Act: -0.0000

Data Index: 241512 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.4852. Min Act: -0.0000

Data Index: 211108 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.4261. Min Act: -0.0000

Data Index: 1898547 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.2651. Min Act: -0.0000

Data Index: 1670052 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.2327. Min Act: -0.0000

Data Index: 1081069 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.0294. Min Act: -0.0000

Data Index: 909460 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.3140. Min Act: -0.0000

Data Index: 1077231 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 4.0514. Min Range: -4.0514

Max Act: 2.8463. Min Act: -0.0000

Data Index: 482751 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.1267. Min Act: -0.0000

Data Index: 36416 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1602296 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 4.0514. Min Range: -4.0514

Max Act: 2.8055. Min Act: -0.0000

Data Index: 868637 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 4.0514. Min Range: -4.0514

Max Act: 2.8867. Min Act: -0.0000

Data Index: 279228 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 4.0514. Min Range: -4.0514

Max Act: 2.9107. Min Act: -0.0000

Data Index: 579272 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 4.0514. Min Range: -4.0514

Max Act: 2.9399. Min Act: -0.0000

Data Index: 535057 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.0497. Min Act: -0.0000

Data Index: 1243258 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 4.0514. Min Range: -4.0514

Max Act: 3.0528. Min Act: -0.0000

Data Index: 1013712 (The Pile)

Max Activating Token Index: 512