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

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

Neuron 4860 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: 0.5070. Min Range: -0.5070

Max Act: 0.5070. Min Act: -0.0000

Data Index: 542884 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1293474 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4619. Min Act: -0.0000

Data Index: 376184 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4431. Min Act: -0.0000

Data Index: 688758 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1323320 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4236. Min Act: -0.0000

Data Index: 699859 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4242. Min Act: -0.0000

Data Index: 190796 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3959. Min Act: -0.0000

Data Index: 689370 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4048. Min Act: -0.0000

Data Index: 657195 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1023056 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1248236 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1074526 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.4066. Min Act: -0.0000

Data Index: 785778 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1034161 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1216954 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3611. Min Act: -0.0000

Data Index: 845957 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3530. Min Act: -0.0001

Data Index: 78815 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3621. Min Act: -0.0000

Data Index: 181532 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3482. Min Act: -0.0000

Data Index: 919083 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.5070. Min Range: -0.5070

Max Act: 0.3467. Min Act: -0.0000

Data Index: 988452 (C4 (Web Text))

Max Activating Token Index: 385