Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3100 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2252. Min Act: -0.0001

Data Index: 887329 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1153473 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2684. Min Act: -0.0001

Data Index: 353135 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2837. Min Act: -0.0001

Data Index: 697666 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2581. Min Act: -0.0001

Data Index: 300357 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2684. Min Act: -0.0001

Data Index: 255231 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2787. Min Act: -0.0001

Data Index: 167256 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1213258 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.1948. Min Act: -0.0001

Data Index: 822828 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2552. Min Act: -0.0001

Data Index: 365676 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2509. Min Act: -0.0001

Data Index: 1168940 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2341. Min Act: -0.0001

Data Index: 639072 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.3083. Min Act: -0.0001

Data Index: 317153 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2273. Min Act: -0.0001

Data Index: 91949 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2239. Min Act: -0.0001

Data Index: 871075 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2470. Min Act: -0.0001

Data Index: 842381 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2338. Min Act: -0.0001

Data Index: 545592 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2699. Min Act: -0.0001

Data Index: 282572 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1069276 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.3083. Min Range: -0.3083

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1239402 (C4 (Web Text))

Max Activating Token Index: 573