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

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

Neuron 4924 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: 2.4007. Min Range: -2.4007

Max Act: 2.4007. Min Act: -0.0000

Data Index: 344530 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.3955. Min Act: -0.0000

Data Index: 166390 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.3295. Min Act: -0.0000

Data Index: 541500 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1113. Min Act: -0.0000

Data Index: 525285 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1091. Min Act: -0.0000

Data Index: 391305 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1997. Min Act: -0.0000

Data Index: 1227458 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1825. Min Act: -0.0000

Data Index: 1114837 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1833. Min Act: -0.0000

Data Index: 301855 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.0179. Min Act: -0.0001

Data Index: 1025558 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.2049. Min Act: -0.0000

Data Index: 497452 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 2.4007. Min Range: -2.4007

Max Act: 1.9663. Min Act: -0.0000

Data Index: 790088 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.0649. Min Act: -0.0000

Data Index: 689010 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.0573. Min Act: -0.0000

Data Index: 1211049 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 2.4007. Min Range: -2.4007

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1078954 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.0410. Min Act: -0.0000

Data Index: 210938 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.1128. Min Act: -0.0000

Data Index: 658151 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 2.4007. Min Range: -2.4007

Max Act: 2.0904. Min Act: -0.0000

Data Index: 1048539 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.4007. Min Range: -2.4007

Max Act: 1.9824. Min Act: -0.0000

Data Index: 280259 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.4007. Min Range: -2.4007

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1049586 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.4007. Min Range: -2.4007

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1175294 (C4 (Web Text))

Max Activating Token Index: 885