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

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

Neuron 2515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.4106. Min Act: -0.0001

Data Index: 931753 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.2548. Min Act: -0.0001

Data Index: 1532740 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.2719. Min Act: -0.0001

Data Index: 749216 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0978. Min Act: -0.0001

Data Index: 1401565 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.2322. Min Act: -0.0001

Data Index: 1525853 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.1467. Min Act: -0.0001

Data Index: 128993 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0697. Min Act: -0.0001

Data Index: 1551471 (Python Code)

Max Activating Token Index: 223

Text #7

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1211132 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.1850. Min Act: -0.0001

Data Index: 604064 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.1294. Min Act: -0.0001

Data Index: 811048 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0742. Min Act: -0.0001

Data Index: 822163 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0629. Min Act: -0.0001

Data Index: 217765 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1579882 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0819. Min Act: -0.0001

Data Index: 1075775 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.4106. Min Range: -1.4106

Max Act: 0.9713. Min Act: -0.0001

Data Index: 1565107 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 1.4106. Min Range: -1.4106

Max Act: 0.9774. Min Act: -0.0001

Data Index: 1096641 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0339. Min Act: -0.0001

Data Index: 1524021 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 1.4106. Min Range: -1.4106

Max Act: 0.9661. Min Act: -0.0001

Data Index: 958423 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0159. Min Act: -0.0001

Data Index: 970221 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.4106. Min Range: -1.4106

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1236869 (C4 (Web Text))

Max Activating Token Index: 992