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

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

Neuron 5190 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: 1.2340. Min Range: -1.2340

Max Act: 1.2340. Min Act: -0.0000

Data Index: 687641 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1320386 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.1383. Min Act: -0.0000

Data Index: 329448 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.1284. Min Act: -0.0000

Data Index: 99903 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.0359. Min Act: -0.0000

Data Index: 459960 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.2340. Min Range: -1.2340

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1216897 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9225. Min Act: -0.0000

Data Index: 977845 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9788. Min Act: -0.0000

Data Index: 489053 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9729. Min Act: -0.0000

Data Index: 477602 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1414664 (Python Code)

Max Activating Token Index: 940

Text #10

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9314. Min Act: -0.0000

Data Index: 917390 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1279343 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8858. Min Act: -0.0000

Data Index: 626156 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8612. Min Act: -0.0000

Data Index: 422167 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9091. Min Act: -0.0000

Data Index: 441254 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9018. Min Act: -0.0000

Data Index: 232309 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.9037. Min Act: -0.0000

Data Index: 730105 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8789. Min Act: -0.0000

Data Index: 799773 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1011059 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.2340. Min Range: -1.2340

Max Act: 0.8701. Min Act: -0.0000

Data Index: 548832 (C4 (Web Text))

Max Activating Token Index: 696