Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2331 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0763. Min Act: -0.0000

Data Index: 585943 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.2235. Min Act: -0.0000

Data Index: 527646 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.8503. Min Act: -0.0000

Data Index: 358450 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9474. Min Act: -0.0000

Data Index: 97668 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1052. Min Act: -0.0000

Data Index: 1244039 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1229. Min Act: -0.0000

Data Index: 1202991 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0989. Min Act: -0.0000

Data Index: 149044 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.1142. Min Act: -0.0000

Data Index: 489397 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.2393. Min Act: -0.0000

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0456. Min Act: -0.0000

Data Index: 1223500 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0128. Min Act: -0.0000

Data Index: 171026 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.8462. Min Act: -0.0000

Data Index: 555575 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0067. Min Act: -0.0000

Data Index: 340368 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0017. Min Act: -0.0000

Data Index: 566333 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0038. Min Act: -0.0000

Data Index: 5187 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.8244. Min Act: -0.0000

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0095. Min Act: -0.0000

Data Index: 894894 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0057. Min Act: -0.0000

Data Index: 84490 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 4.2393. Min Range: -4.2393

Max Act: 3.9787. Min Act: -0.0000

Data Index: 559144 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 4.2393. Min Range: -4.2393

Max Act: 4.0031. Min Act: -0.0000

Data Index: 40177 (C4 (Web Text))

Max Activating Token Index: 805