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

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

Neuron 1480 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2210. Min Range: -1.2210

Max Act: 1.2210. Min Act: -0.0001

Data Index: 1106225 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.2210. Min Range: -1.2210

Max Act: 1.0771. Min Act: -0.0001

Data Index: 18901 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.9879. Min Act: -0.0001

Data Index: 553396 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.9380. Min Act: -0.0001

Data Index: 122090 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1016883 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8875. Min Act: -0.0001

Data Index: 1154958 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.9044. Min Act: -0.0001

Data Index: 459308 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8869. Min Act: -0.0001

Data Index: 432861 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8645. Min Act: -0.0001

Data Index: 763082 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8972. Min Act: -0.0001

Data Index: 937551 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1075403 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8125. Min Act: -0.0001

Data Index: 984940 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.7976. Min Act: -0.0001

Data Index: 989359 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8212. Min Act: -0.0001

Data Index: 787048 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8279. Min Act: -0.0001

Data Index: 1063466 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8185. Min Act: -0.0001

Data Index: 749984 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.7865. Min Act: -0.0001

Data Index: 585635 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8252. Min Act: -0.0001

Data Index: 338429 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8763. Min Act: -0.0001

Data Index: 296958 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 1.2210. Min Range: -1.2210

Max Act: 0.8110. Min Act: -0.0001

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 553