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

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

Neuron 889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1296792 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1310. Min Act: -0.0001

Data Index: 488640 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1165. Min Act: -0.0001

Data Index: 197981 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1337997 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1081. Min Act: -0.0001

Data Index: 95146 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1091. Min Act: -0.0001

Data Index: 416802 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1042. Min Act: -0.0001

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1118. Min Act: -0.0001

Data Index: 291383 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1094. Min Act: -0.0001

Data Index: 779728 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1088. Min Act: -0.0001

Data Index: 292305 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1120. Min Act: -0.0001

Data Index: 199781 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1569739 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1024958 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1139554 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1241747 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1472935 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1210784 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1047. Min Act: -0.0001

Data Index: 18888 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0963. Min Act: -0.0001

Data Index: 359522 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1004. Min Act: -0.0001

Data Index: 183660 (C4 (Web Text))

Max Activating Token Index: 283