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

Dataset: The Pile

Neuron 3482 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: 1.1344. Min Range: -1.1344

Max Act: 1.1344. Min Act: -0.0000

Data Index: 936041 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0388. Min Act: -0.0000

Data Index: 465394 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0606. Min Act: -0.0000

Data Index: 880120 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1125788 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1351438 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0344. Min Act: -0.0000

Data Index: 646542 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0701. Min Act: -0.0000

Data Index: 984522 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9919. Min Act: -0.0000

Data Index: 537423 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1662390 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1429594 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1408565 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1765731 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0166. Min Act: -0.0000

Data Index: 643497 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9524. Min Act: -0.0000

Data Index: 526800 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9581. Min Act: -0.0000

Data Index: 621855 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0136. Min Act: -0.0000

Data Index: 888575 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9685. Min Act: -0.0000

Data Index: 72486 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1970630 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.1344. Min Range: -1.1344

Max Act: 1.0242. Min Act: -0.0000

Data Index: 604753 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 1.1344. Min Range: -1.1344

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1551049 (The Pile)

Max Activating Token Index: 491