Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 98 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7949. Min Act: -0.0004

Data Index: 1259896 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7624. Min Act: -0.0004

Data Index: 348144 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7052. Min Act: -0.0004

Data Index: 388729 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6995. Min Act: -0.0004

Data Index: 1333459 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7136. Min Act: -0.0004

Data Index: 51381 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6740. Min Act: -0.0004

Data Index: 661577 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6881. Min Act: -0.0004

Data Index: 743405 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7063. Min Act: -0.0004

Data Index: 119188 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6738. Min Act: -0.0004

Data Index: 41130 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6928. Min Act: -0.0004

Data Index: 1302650 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6551. Min Act: -0.0004

Data Index: 103909 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6546. Min Act: -0.0004

Data Index: 1028355 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6638. Min Act: -0.0004

Data Index: 782187 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6387. Min Act: -0.0004

Data Index: 1283767 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6378. Min Act: -0.0004

Data Index: 1169291 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6561. Min Act: -0.0004

Data Index: 134075 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6322. Min Act: -0.0004

Data Index: 302028 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6302. Min Act: -0.0004

Data Index: 949057 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6071. Min Act: -0.0004

Data Index: 58134 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5868. Min Act: -0.0004

Data Index: 944727 (C4 (Web Text))

Max Activating Token Index: 596