Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.3968. Min Act: -0.0001

Data Index: 604835 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.3041. Min Act: -0.0001

Data Index: 940770 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1656. Min Act: -0.0001

Data Index: 1218829 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.2208. Min Act: -0.0001

Data Index: 904923 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.2201. Min Act: -0.0001

Data Index: 547591 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.2078. Min Act: -0.0001

Data Index: 906415 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1792. Min Act: -0.0001

Data Index: 385635 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1432. Min Act: -0.0001

Data Index: 1084538 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.2007. Min Act: -0.0001

Data Index: 132591 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1183. Min Act: -0.0001

Data Index: 1103867 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1484. Min Act: -0.0001

Data Index: 801417 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1102. Min Act: -0.0001

Data Index: 1143232 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1388. Min Act: -0.0001

Data Index: 1087381 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.0746. Min Act: -0.0001

Data Index: 894779 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1328. Min Act: -0.0001

Data Index: 1291479 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1008. Min Act: -0.0001

Data Index: 383263 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1379. Min Act: -0.0001

Data Index: 204082 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1796. Min Act: -0.0001

Data Index: 882968 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.0404. Min Act: -0.0001

Data Index: 675615 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.3968. Min Range: -1.3968

Max Act: 1.1459. Min Act: -0.0001

Data Index: 729538 (C4 (Web Text))

Max Activating Token Index: 160