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

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

Neuron 4029 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0001

Data Index: 367701 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0985. Min Act: -0.0000

Data Index: 659526 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1042. Min Act: -0.0000

Data Index: 321917 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1003604 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1123654 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1018577 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1315180 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1004. Min Act: -0.0001

Data Index: 70378 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1206711 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1298147 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0959. Min Act: -0.0000

Data Index: 371223 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0916. Min Act: -0.0001

Data Index: 384605 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0909. Min Act: -0.0000

Data Index: 931223 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1260310 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0941. Min Act: -0.0001

Data Index: 441981 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0885. Min Act: -0.0000

Data Index: 233188 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1572426 (Python Code)

Max Activating Token Index: 308

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1097201 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0782. Min Act: -0.0000

Data Index: 339063 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0814. Min Act: -0.0000

Data Index: 296142 (C4 (Web Text))

Max Activating Token Index: 400