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

Dataset: The Pile

Neuron 123 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: 3.9667. Min Range: -3.9667

Max Act: 3.4870. Min Act: -0.0000

Data Index: 28533 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.0000

Data Index: 869483 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8075. Min Act: -0.0000

Data Index: 674005 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5798. Min Act: -0.0000

Data Index: 1489130 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9039. Min Act: -0.0000

Data Index: 1664257 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6845. Min Act: -0.0000

Data Index: 500819 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6936. Min Act: -0.0000

Data Index: 1675562 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8289. Min Act: -0.0000

Data Index: 1562797 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6714. Min Act: -0.0000

Data Index: 1718917 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8086. Min Act: -0.0000

Data Index: 923634 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5089. Min Act: -0.0000

Data Index: 195122 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6641. Min Act: -0.0000

Data Index: 897516 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.3264. Min Act: -0.0000

Data Index: 1177841 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6123. Min Act: -0.0000

Data Index: 1776394 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.4587. Min Act: -0.0000

Data Index: 990596 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.6162. Min Act: -0.0000

Data Index: 1001165 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.4519. Min Act: -0.0000

Data Index: 470684 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7330. Min Act: -0.0000

Data Index: 1346007 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.7304. Min Act: -0.0000

Data Index: 1383997 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.5448. Min Act: -0.0000

Data Index: 1834016 (The Pile)

Max Activating Token Index: 419