Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2816 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.5857. Min Act: -0.0000

Data Index: 966690 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.6926. Min Act: -0.0000

Data Index: 947944 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.2869. Min Act: -0.0000

Data Index: 924515 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1023882 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.2050. Min Act: -0.0000

Data Index: 311280 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.1858. Min Act: -0.0000

Data Index: 1065143 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.1697. Min Act: -0.0000

Data Index: 244876 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.0983. Min Act: -0.0000

Data Index: 297003 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1538030 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.0317. Min Act: -0.0000

Data Index: 1338573 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.0029. Min Act: -0.0000

Data Index: 28288 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 2.6926. Min Range: -2.6926

Max Act: 2.0027. Min Act: -0.0000

Data Index: 1180454 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9950. Min Act: -0.0000

Data Index: 96859 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1520099 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1266043 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9448. Min Act: -0.0000

Data Index: 357951 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9499. Min Act: -0.0000

Data Index: 184487 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9344. Min Act: -0.0000

Data Index: 592510 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.9349. Min Act: -0.0000

Data Index: 721884 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 2.6926. Min Range: -2.6926

Max Act: 1.8211. Min Act: -0.0000

Data Index: 282286 (C4 (Web Text))

Max Activating Token Index: 734