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

Dataset: The Pile

Neuron 3251 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: 2.4000. Min Range: -2.4000

Max Act: 2.2557. Min Act: -0.0000

Data Index: 776487 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.2488. Min Act: -0.0000

Data Index: 565465 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.3528. Min Act: -0.0000

Data Index: 717337 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.4000. Min Act: -0.0000

Data Index: 1681172 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.2696. Min Act: -0.0000

Data Index: 625585 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.1199. Min Act: -0.0000

Data Index: 458679 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.0595. Min Act: -0.0000

Data Index: 1062227 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.1318. Min Act: -0.0000

Data Index: 509200 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.2445. Min Act: -0.0000

Data Index: 1067465 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.8817. Min Act: -0.0000

Data Index: 692278 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.1900. Min Act: -0.0000

Data Index: 437228 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.0595. Min Act: -0.0000

Data Index: 1194291 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.0342. Min Act: -0.0000

Data Index: 1142350 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.2389. Min Act: -0.0000

Data Index: 1807481 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9140. Min Act: -0.0000

Data Index: 47307 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.8925. Min Act: -0.0000

Data Index: 1317483 (The Pile)

Max Activating Token Index: 923

Text #16

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.1158. Min Act: -0.0000

Data Index: 750933 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.8754. Min Act: -0.0000

Data Index: 1798595 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9440. Min Act: -0.0000

Data Index: 538021 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7574. Min Act: -0.0000

Data Index: 1393524 (The Pile)

Max Activating Token Index: 193