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

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

Neuron 4667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.1869. Min Act: -0.0001

Data Index: 231848 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0433. Min Act: -0.0001

Data Index: 1040788 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0534. Min Act: -0.0001

Data Index: 806010 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9332. Min Act: -0.0001

Data Index: 114101 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9973. Min Act: -0.0001

Data Index: 924879 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9845. Min Act: -0.0001

Data Index: 979954 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9796. Min Act: -0.0001

Data Index: 1141642 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9811. Min Act: -0.0001

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9875. Min Act: -0.0001

Data Index: 578645 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9249. Min Act: -0.0001

Data Index: 244874 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9652. Min Act: -0.0001

Data Index: 280919 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.8098. Min Act: -0.0001

Data Index: 169111 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.7796. Min Act: -0.0001

Data Index: 267212 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.8955. Min Act: -0.0001

Data Index: 289375 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9747. Min Act: -0.0001

Data Index: 224948 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.7471. Min Act: -0.0001

Data Index: 165597 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9155. Min Act: -0.0001

Data Index: 31455 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1027113 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9132. Min Act: -0.0001

Data Index: 620642 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.8272. Min Act: -0.0001

Data Index: 740835 (C4 (Web Text))

Max Activating Token Index: 15