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

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

Neuron 4842 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1339470 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1346036 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1207540 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1435. Min Act: -0.0000

Data Index: 733404 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1452. Min Act: -0.0000

Data Index: 417379 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1085881 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1183663 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1286. Min Act: -0.0000

Data Index: 604385 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0879. Min Act: -0.0000

Data Index: 818529 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0682. Min Act: -0.0000

Data Index: 986847 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9801. Min Act: -0.0000

Data Index: 318545 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1048322 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9942. Min Act: -0.0000

Data Index: 521188 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9558. Min Act: -0.0000

Data Index: 191020 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0331. Min Act: -0.0000

Data Index: 671544 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9591. Min Act: -0.0000

Data Index: 157188 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1267038 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9209. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1095083 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1174240 (C4 (Web Text))

Max Activating Token Index: 297