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

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

Neuron 5045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1237. Min Range: -1.1237

Max Act: 1.1237. Min Act: -0.0000

Data Index: 924044 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 1.1237. Min Range: -1.1237

Max Act: 1.0983. Min Act: -0.0000

Data Index: 523816 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.8759. Min Act: -0.0000

Data Index: 54689 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.8319. Min Act: -0.0000

Data Index: 686967 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.8722. Min Act: -0.0000

Data Index: 921085 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1277019 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1283366 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1119890 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1267239 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1174712 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1457720 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7417. Min Act: -0.0000

Data Index: 577503 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7033. Min Act: -0.0000

Data Index: 453743 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.7190. Min Act: -0.0000

Data Index: 159196 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6708. Min Act: -0.0000

Data Index: 364184 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6741. Min Act: -0.0000

Data Index: 556870 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6862. Min Act: -0.0000

Data Index: 341999 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6593. Min Act: -0.0000

Data Index: 822334 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6833. Min Act: -0.0001

Data Index: 40196 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.1237. Min Range: -1.1237

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1259958 (C4 (Web Text))

Max Activating Token Index: 938