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

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

Neuron 1693 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1203918 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6935. Min Act: -0.0000

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.7070. Min Act: -0.0000

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6201. Min Act: -0.0000

Data Index: 857979 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1364221 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6336. Min Act: -0.0000

Data Index: 617253 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6077. Min Act: -0.0000

Data Index: 996153 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5967. Min Act: -0.0000

Data Index: 464705 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1574651 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1308553 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1517310 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5663. Min Act: -0.0000

Data Index: 341753 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5860. Min Act: -0.0000

Data Index: 479136 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1086307 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5541. Min Act: -0.0000

Data Index: 231679 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5528. Min Act: -0.0000

Data Index: 906678 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5038. Min Act: -0.0000

Data Index: 812167 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5303. Min Act: -0.0000

Data Index: 407842 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1331846 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.7567. Min Range: -0.7567

Max Act: 0.5271. Min Act: -0.0000

Data Index: 362060 (C4 (Web Text))

Max Activating Token Index: 417