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

Dataset: The Pile

Neuron 1222 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1116071 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1333117 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1534909 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1686024 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1729045 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6365. Min Act: -0.0000

Data Index: 832480 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5747. Min Act: -0.0000

Data Index: 57341 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6216. Min Act: -0.0000

Data Index: 667112 (The Pile)

Max Activating Token Index: 362

Text #8

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1362204 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5748. Min Act: -0.0000

Data Index: 923348 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5923. Min Act: -0.0000

Data Index: 12253 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1545694 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5568. Min Act: -0.0000

Data Index: 504512 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1910084 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6067. Min Act: -0.0000

Data Index: 977018 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5639. Min Act: -0.0000

Data Index: 317915 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1395562 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5939. Min Act: -0.0000

Data Index: 492128 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5532. Min Act: -0.0000

Data Index: 201286 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1857955 (The Pile)

Max Activating Token Index: 177