Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1597 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.3907. Min Act: 0.0001

Data Index: 740974 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.3069. Min Act: -0.0001

Data Index: 581884 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2801. Min Act: 0.0001

Data Index: 4386 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2707. Min Act: -0.0000

Data Index: 62078 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1335526 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2725. Min Act: -0.0001

Data Index: 228782 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2626. Min Act: 0.0001

Data Index: 1088875 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2599. Min Act: -0.0000

Data Index: 647713 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1192294 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2593. Min Act: -0.0001

Data Index: 895435 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2523. Min Act: -0.0001

Data Index: 773296 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2424. Min Act: -0.0000

Data Index: 927924 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2536. Min Act: -0.0000

Data Index: 925287 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2449. Min Act: 0.0001

Data Index: 227398 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2431. Min Act: -0.0001

Data Index: 460508 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2418. Min Act: 0.0001

Data Index: 920992 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1004187 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2345. Min Act: 0.0001

Data Index: 1354483 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2343. Min Act: 0.0001

Data Index: 563064 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.3907. Min Range: -0.3907

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1169053 (C4 (Web Text))

Max Activating Token Index: 167