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

Dataset: The Pile

Neuron 3963 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: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0000

Data Index: 451901 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1807576 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5596. Min Act: -0.0000

Data Index: 312804 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6483. Min Act: -0.0000

Data Index: 47074 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6100. Min Act: -0.0000

Data Index: 728016 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6059. Min Act: -0.0000

Data Index: 373129 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1245312 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1368721 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6410. Min Act: -0.0000

Data Index: 573760 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1903560 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1638672 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1909123 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1998242 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1461029 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1877204 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1391032 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1637738 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5613. Min Act: -0.0000

Data Index: 453706 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5904. Min Act: -0.0000

Data Index: 574528 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6051. Min Act: -0.0000

Data Index: 330533 (The Pile)

Max Activating Token Index: 312