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

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

Neuron 5096 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1649626 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1003484 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1432805 (Python Code)

Max Activating Token Index: 996

Text #3

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.3679. Min Act: -0.0000

Data Index: 219244 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1520694 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1125288 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.3806. Min Act: -0.0000

Data Index: 791996 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1580945 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1317110 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.3353. Min Act: -0.0000

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1477752 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2248. Min Act: -0.0000

Data Index: 701998 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1248279 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.3337. Min Act: -0.0000

Data Index: 692128 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1479931 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2427. Min Act: -0.0000

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1106089 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1215491 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.2113. Min Act: -0.0000

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.7340. Min Range: -1.7340

Max Act: 1.1950. Min Act: -0.0000

Data Index: 976616 (C4 (Web Text))

Max Activating Token Index: 305