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

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

Neuron 1719 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.8345. Min Act: -0.0001

Data Index: 763859 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 4.2918. Min Range: -4.2918

Max Act: 4.2918. Min Act: -0.0001

Data Index: 898787 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.8372. Min Act: -0.0000

Data Index: 890706 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.5268. Min Act: -0.0001

Data Index: 882058 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.8206. Min Act: -0.0001

Data Index: 967199 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.6929. Min Act: -0.0000

Data Index: 1255717 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4577. Min Act: -0.0001

Data Index: 58021 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.9155. Min Act: -0.0000

Data Index: 1302154 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.3860. Min Act: -0.0000

Data Index: 951071 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.5881. Min Act: -0.0001

Data Index: 849379 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4715. Min Act: -0.0000

Data Index: 618230 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4188. Min Act: -0.0001

Data Index: 227205 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4420. Min Act: -0.0000

Data Index: 646514 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4804. Min Act: -0.0001

Data Index: 102074 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4051. Min Act: -0.0001

Data Index: 1273973 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.5326. Min Act: -0.0001

Data Index: 1279635 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4067. Min Act: -0.0000

Data Index: 1215963 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.4041. Min Act: -0.0000

Data Index: 55573 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.6435. Min Act: -0.0000

Data Index: 1241178 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 4.2918. Min Range: -4.2918

Max Act: 3.1617. Min Act: -0.0000

Data Index: 1220165 (C4 (Web Text))

Max Activating Token Index: 517