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

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

Neuron 1658 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: 2.2710. Min Range: -2.2710

Max Act: 2.2710. Min Act: -0.0000

Data Index: 1165395 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1368. Min Act: -0.0000

Data Index: 973994 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1601594 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0514. Min Act: -0.0000

Data Index: 472321 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9847. Min Act: -0.0000

Data Index: 296704 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.2016. Min Act: -0.0000

Data Index: 853267 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0197. Min Act: -0.0001

Data Index: 8148 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1280. Min Act: -0.0000

Data Index: 947323 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1169. Min Act: -0.0000

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0613. Min Act: -0.0000

Data Index: 568306 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1116. Min Act: -0.0000

Data Index: 22791 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.1404. Min Act: -0.0000

Data Index: 1644625 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9604. Min Act: -0.0000

Data Index: 1084463 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0755. Min Act: -0.0000

Data Index: 696702 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0682. Min Act: -0.0000

Data Index: 519692 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0081. Min Act: -0.0000

Data Index: 432961 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0787. Min Act: -0.0000

Data Index: 1402979 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0494. Min Act: -0.0000

Data Index: 1027369 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 2.2710. Min Range: -2.2710

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1374036 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 2.2710. Min Range: -2.2710

Max Act: 2.0091. Min Act: -0.0000

Data Index: 107612 (C4 (Web Text))

Max Activating Token Index: 557