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

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

Neuron 5070 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0000

Data Index: 526694 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1339023 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0478. Min Act: -0.0000

Data Index: 168392 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0477. Min Act: -0.0000

Data Index: 605755 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0469. Min Act: -0.0000

Data Index: 991978 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0479. Min Act: -0.0000

Data Index: 962815 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0479. Min Act: -0.0000

Data Index: 914640 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0415. Min Act: -0.0000

Data Index: 623726 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0409. Min Act: -0.0000

Data Index: 1143334 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0432. Min Act: -0.0000

Data Index: 641704 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1147103 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0423. Min Act: -0.0000

Data Index: 367828 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0417. Min Act: -0.0000

Data Index: 1095441 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0402. Min Act: -0.0000

Data Index: 69889 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0409. Min Act: -0.0000

Data Index: 162461 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1325683 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1403495 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0388. Min Act: -0.0000

Data Index: 862847 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0367. Min Act: -0.0000

Data Index: 235055 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0394. Min Act: -0.0000

Data Index: 223673 (C4 (Web Text))

Max Activating Token Index: 890