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

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

Neuron 5098 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: 3.8574. Min Range: -3.8574

Max Act: 3.4721. Min Act: -0.0001

Data Index: 1086173 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.8574. Min Act: -0.0000

Data Index: 792943 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.4622. Min Act: -0.0001

Data Index: 360738 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.2086. Min Act: -0.0000

Data Index: 637705 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1874. Min Act: -0.0001

Data Index: 35156 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.2629. Min Act: -0.0001

Data Index: 209369 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1496. Min Act: -0.0000

Data Index: 1021893 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1333. Min Act: -0.0000

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1408. Min Act: -0.0000

Data Index: 243630 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.2720. Min Act: -0.0000

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 3.8574. Min Range: -3.8574

Max Act: 2.9145. Min Act: -0.0000

Data Index: 1068582 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.2066. Min Act: -0.0001

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.0364. Min Act: -0.0000

Data Index: 1042530 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1556. Min Act: -0.0000

Data Index: 509456 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1278. Min Act: -0.0000

Data Index: 294710 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1048. Min Act: -0.0000

Data Index: 662585 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.8574. Min Range: -3.8574

Max Act: 2.9340. Min Act: -0.0000

Data Index: 991752 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 3.8574. Min Range: -3.8574

Max Act: 3.1056. Min Act: -0.0000

Data Index: 100268 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.8574. Min Range: -3.8574

Max Act: 2.9325. Min Act: -0.0000

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 3.8574. Min Range: -3.8574

Max Act: 2.9226. Min Act: -0.0000

Data Index: 788971 (C4 (Web Text))

Max Activating Token Index: 842