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

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

Neuron 3231 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: 1.1397. Min Range: -1.1397

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1024415 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1397. Min Act: -0.0001

Data Index: 915730 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.1118. Min Act: -0.0001

Data Index: 381235 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9152. Min Act: -0.0001

Data Index: 835771 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9777. Min Act: -0.0001

Data Index: 1044591 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9709. Min Act: -0.0001

Data Index: 949295 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9285. Min Act: -0.0001

Data Index: 896175 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.0516. Min Act: -0.0001

Data Index: 1049329 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9874. Min Act: -0.0001

Data Index: 757927 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 1.1397. Min Range: -1.1397

Max Act: 1.0142. Min Act: -0.0001

Data Index: 94244 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7942. Min Act: -0.0001

Data Index: 735687 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9730. Min Act: -0.0001

Data Index: 419001 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9316. Min Act: -0.0001

Data Index: 107136 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.9427. Min Act: -0.0001

Data Index: 325053 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8539. Min Act: -0.0000

Data Index: 221292 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8370. Min Act: -0.0001

Data Index: 415796 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8852. Min Act: -0.0001

Data Index: 1113910 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8896. Min Act: -0.0001

Data Index: 518177 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.7616. Min Act: -0.0001

Data Index: 470701 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.1397. Min Range: -1.1397

Max Act: 0.8169. Min Act: -0.0001

Data Index: 788807 (C4 (Web Text))

Max Activating Token Index: 605