Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1043 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0004

Data Index: 983306 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1098. Min Act: -0.0004

Data Index: 85706 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1039. Min Act: -0.0003

Data Index: 729628 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1091682 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1034. Min Act: -0.0003

Data Index: 176452 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1008. Min Act: -0.0003

Data Index: 670877 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1072554 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1310426 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0988. Min Act: -0.0003

Data Index: 401004 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0970. Min Act: -0.0003

Data Index: 336087 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0881. Min Act: -0.0004

Data Index: 886622 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1009. Min Act: -0.0003

Data Index: 842803 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1191052 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1126046 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1023. Min Act: -0.0004

Data Index: 1325777 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1309756 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1084239 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0937. Min Act: -0.0003

Data Index: 286730 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0902. Min Act: -0.0004

Data Index: 823678 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0931. Min Act: -0.0004

Data Index: 1202026 (C4 (Web Text))

Max Activating Token Index: 560