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

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

Neuron 3948 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.2415. Min Act: -0.0001

Data Index: 2126 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1493. Min Act: -0.0001

Data Index: 21698 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1001. Min Act: -0.0001

Data Index: 438476 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0896. Min Act: -0.0001

Data Index: 114313 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1143. Min Act: -0.0001

Data Index: 362560 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1154532 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.1283. Min Act: -0.0001

Data Index: 236912 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1122059 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0081. Min Act: -0.0001

Data Index: 898710 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0155. Min Act: -0.0001

Data Index: 569271 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9727. Min Act: -0.0000

Data Index: 369053 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1222979 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9294. Min Act: -0.0000

Data Index: 624138 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8961. Min Act: -0.0000

Data Index: 935239 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.9075. Min Act: -0.0001

Data Index: 1150795 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8942. Min Act: -0.0001

Data Index: 569538 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.2415. Min Range: -1.2415

Max Act: 1.0165. Min Act: -0.0001

Data Index: 945386 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1279589 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8940. Min Act: -0.0001

Data Index: 738450 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.2415. Min Range: -1.2415

Max Act: 0.8766. Min Act: -0.0001

Data Index: 883524 (C4 (Web Text))

Max Activating Token Index: 531