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

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

Neuron 3442 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.8676. Min Act: -0.0000

Data Index: 25507 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7989. Min Act: -0.0000

Data Index: 797677 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1132602 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1355967 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1526483 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7018. Min Act: -0.0000

Data Index: 252229 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1256526 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6930. Min Act: -0.0000

Data Index: 205511 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1369402 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6596. Min Act: -0.0000

Data Index: 164547 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1366621 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1634367 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1368144 (Python Code)

Max Activating Token Index: 404

Text #13

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1416650 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1555044 (Python Code)

Max Activating Token Index: 869

Text #15

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1416873 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1476336 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1603071 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1225399 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.8676. Min Range: -0.8676

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1606990 (Python Code)

Max Activating Token Index: 304