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

Dataset: The Pile

Neuron 1269 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: 1.9548. Min Range: -1.9548

Max Act: 1.9548. Min Act: -0.0000

Data Index: 1969145 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1255818 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.3037. Min Act: -0.0000

Data Index: 73253 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.2953. Min Act: -0.0000

Data Index: 943894 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.2595. Min Act: -0.0000

Data Index: 1003467 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.2452. Min Act: -0.0000

Data Index: 592010 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1430246 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.1348. Min Act: -0.0000

Data Index: 548450 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0353. Min Act: -0.0000

Data Index: 905723 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0595. Min Act: -0.0000

Data Index: 282914 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0581. Min Act: -0.0000

Data Index: 271424 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0792. Min Act: -0.0000

Data Index: 299633 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1935152 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1098918 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 1.9548. Min Range: -1.9548

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1975333 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1771340 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1981786 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9598. Min Act: -0.0000

Data Index: 438525 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1701606 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 1.9548. Min Range: -1.9548

Max Act: 0.9133. Min Act: -0.0000

Data Index: 852988 (The Pile)

Max Activating Token Index: 961