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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1640058 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1010834 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.8064. Min Act: -0.0000

Data Index: 335068 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7426. Min Act: -0.0000

Data Index: 767554 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7104. Min Act: -0.0000

Data Index: 331046 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6847. Min Act: -0.0000

Data Index: 385964 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6866. Min Act: -0.0000

Data Index: 587693 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6231. Min Act: -0.0000

Data Index: 578040 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6208. Min Act: -0.0000

Data Index: 842109 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6238. Min Act: -0.0000

Data Index: 981453 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6045. Min Act: -0.0000

Data Index: 581339 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6183. Min Act: -0.0000

Data Index: 662952 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.7057. Min Act: -0.0001

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5682. Min Act: -0.0000

Data Index: 867718 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6024. Min Act: -0.0000

Data Index: 758307 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5970. Min Act: -0.0000

Data Index: 743561 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1193983 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.6049. Min Act: -0.0000

Data Index: 132217 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5582. Min Act: -0.0000

Data Index: 520399 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.8148. Min Range: -0.8148

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1246635 (C4 (Web Text))

Max Activating Token Index: 580