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

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

Neuron 2343 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: 2.9057. Min Range: -2.9057

Max Act: 2.8939. Min Act: -0.0000

Data Index: 338493 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.8796. Min Act: -0.0000

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.9057. Min Act: -0.0000

Data Index: 637049 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.6855. Min Act: -0.0000

Data Index: 961775 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4234. Min Act: -0.0000

Data Index: 689086 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.6027. Min Act: -0.0000

Data Index: 263906 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.5259. Min Act: -0.0000

Data Index: 118974 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.6405. Min Act: -0.0000

Data Index: 907199 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.3548. Min Act: -0.0000

Data Index: 915802 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4431. Min Act: -0.0000

Data Index: 903196 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1344778 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4171. Min Act: -0.0000

Data Index: 491789 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4092. Min Act: -0.0000

Data Index: 1269534 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.2750. Min Act: -0.0000

Data Index: 83321 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.3859. Min Act: -0.0000

Data Index: 1256744 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.3816. Min Act: -0.0000

Data Index: 412746 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.4050. Min Act: -0.0000

Data Index: 578377 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.2515. Min Act: -0.0000

Data Index: 867868 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.5006. Min Act: -0.0000

Data Index: 515666 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 2.9057. Min Range: -2.9057

Max Act: 2.3936. Min Act: -0.0000

Data Index: 308848 (C4 (Web Text))

Max Activating Token Index: 929