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

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

Neuron 3957 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1152054 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1089101 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.0253. Min Act: -0.0001

Data Index: 899214 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1336693 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.0050. Min Act: -0.0000

Data Index: 482141 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.2558. Min Range: -1.2558

Max Act: 1.0008. Min Act: -0.0000

Data Index: 684379 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1337513 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9197. Min Act: -0.0000

Data Index: 1156774 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9649. Min Act: -0.0001

Data Index: 1147321 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1138217 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.9241. Min Act: -0.0001

Data Index: 1288345 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8377. Min Act: -0.0000

Data Index: 376330 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8091. Min Act: -0.0001

Data Index: 858576 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8881. Min Act: -0.0001

Data Index: 710842 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8259. Min Act: -0.0001

Data Index: 578490 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1072596 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8377. Min Act: -0.0001

Data Index: 554197 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1104820 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.8368. Min Act: -0.0000

Data Index: 326200 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.2558. Min Range: -1.2558

Max Act: 0.7908. Min Act: -0.0000

Data Index: 113778 (C4 (Web Text))

Max Activating Token Index: 785