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

Dataset: The Pile

Neuron 987 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: 0.3721. Min Range: -0.3721

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1107725 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0000

Data Index: 474000 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1441873 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1959309 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1262267 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1921909 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1877627 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3415. Min Act: -0.0000

Data Index: 436649 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3207. Min Act: -0.0000

Data Index: 761477 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3418. Min Act: -0.0000

Data Index: 589806 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3408. Min Act: -0.0000

Data Index: 702322 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3157. Min Act: -0.0000

Data Index: 446248 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3060. Min Act: -0.0000

Data Index: 919 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1633004 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1670541 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1244246 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3230. Min Act: -0.0000

Data Index: 604905 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3293. Min Act: -0.0000

Data Index: 741182 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1891032 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3108. Min Act: -0.0000

Data Index: 994936 (The Pile)

Max Activating Token Index: 422