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

Dataset: The Pile

Neuron 2843 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9401. Min Act: -0.0000

Data Index: 470257 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9812. Min Act: -0.0000

Data Index: 102076 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1196198 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1534189 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1934168 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0810. Min Act: -0.0000

Data Index: 837024 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1437293 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1836809 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9985. Min Act: -0.0001

Data Index: 1328974 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9681. Min Act: -0.0001

Data Index: 1031204 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9713. Min Act: -0.0001

Data Index: 59998 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0412. Min Act: -0.0000

Data Index: 286054 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9777. Min Act: -0.0001

Data Index: 133152 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9518. Min Act: -0.0000

Data Index: 597536 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1367948 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1018226 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9005. Min Act: -0.0001

Data Index: 837939 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0026. Min Act: -0.0000

Data Index: 566255 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.0810. Min Range: -1.0810

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1981538 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.0810. Min Range: -1.0810

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1205386 (The Pile)

Max Activating Token Index: 143