Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 170 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1694. Min Act: -0.0001

Data Index: 203343 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1239. Min Act: -0.0001

Data Index: 450595 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1214. Min Act: -0.0001

Data Index: 643421 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1259. Min Act: -0.0001

Data Index: 571744 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1180. Min Act: -0.0001

Data Index: 179641 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1044. Min Act: -0.0001

Data Index: 965692 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1042. Min Act: -0.0001

Data Index: 739329 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1232491 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1248920 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1063. Min Act: -0.0001

Data Index: 692306 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1013. Min Act: -0.0001

Data Index: 834598 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1223173 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1001. Min Act: -0.0001

Data Index: 132198 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1031. Min Act: -0.0001

Data Index: 786319 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1020. Min Act: -0.0001

Data Index: 806882 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1023772 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0999. Min Act: -0.0001

Data Index: 795082 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1090018 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0949. Min Act: -0.0001

Data Index: 955186 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0981. Min Act: -0.0001

Data Index: 52864 (C4 (Web Text))

Max Activating Token Index: 255