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

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

Neuron 993 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: 0.1092. Min Range: -0.1092

Max Act: 0.1092. Min Act: -0.0003

Data Index: 158797 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1047. Min Act: -0.0004

Data Index: 1433 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1034. Min Act: -0.0003

Data Index: 31529 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1003. Min Act: -0.0003

Data Index: 823070 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1004. Min Act: -0.0003

Data Index: 1130159 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0992. Min Act: -0.0003

Data Index: 527530 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0998. Min Act: -0.0002

Data Index: 278607 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0974. Min Act: -0.0003

Data Index: 836621 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0991. Min Act: -0.0003

Data Index: 768811 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0960. Min Act: -0.0001

Data Index: 381663 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0935. Min Act: -0.0003

Data Index: 585859 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0947. Min Act: -0.0003

Data Index: 1260289 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0945. Min Act: -0.0003

Data Index: 389617 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0932. Min Act: -0.0003

Data Index: 477058 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0920. Min Act: -0.0003

Data Index: 1080358 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0910. Min Act: -0.0004

Data Index: 233781 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0943. Min Act: -0.0004

Data Index: 465362 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0936. Min Act: -0.0003

Data Index: 1249882 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0917. Min Act: -0.0004

Data Index: 88885 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1164551 (C4 (Web Text))

Max Activating Token Index: 453