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

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

Neuron 3812 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0000

Data Index: 217738 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1199720 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1195. Min Act: -0.0000

Data Index: 358501 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1091. Min Act: -0.0000

Data Index: 652525 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1069833 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1173263 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0963. Min Act: -0.0000

Data Index: 429420 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0907. Min Act: -0.0000

Data Index: 303933 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0930. Min Act: -0.0000

Data Index: 186617 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1319906 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0841. Min Act: 0.0000

Data Index: 1275066 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0919. Min Act: -0.0000

Data Index: 73750 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1068294 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0931. Min Act: -0.0000

Data Index: 21487 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0886. Min Act: -0.0000

Data Index: 572467 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1188673 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0914. Min Act: -0.0000

Data Index: 421378 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0904. Min Act: -0.0000

Data Index: 511966 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1177971 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0818. Min Act: -0.0000

Data Index: 986663 (C4 (Web Text))

Max Activating Token Index: 845