Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1248141 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0000

Data Index: 705877 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1278550 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1615. Min Act: -0.0000

Data Index: 79304 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1345. Min Act: -0.0000

Data Index: 65476 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1207. Min Act: -0.0000

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1245. Min Act: -0.0001

Data Index: 422062 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1195. Min Act: -0.0000

Data Index: 242011 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1189. Min Act: -0.0000

Data Index: 569981 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1091419 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1124. Min Act: -0.0000

Data Index: 576758 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1107. Min Act: -0.0000

Data Index: 72553 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1070. Min Act: -0.0000

Data Index: 588568 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1129. Min Act: -0.0000

Data Index: 37077 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1107. Min Act: -0.0000

Data Index: 870621 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1171792 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1063. Min Act: -0.0000

Data Index: 476994 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1100840 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1262945 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.0958. Min Act: -0.0000

Data Index: 570480 (C4 (Web Text))

Max Activating Token Index: 188