Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0469. Min Range: -1.0469

Max Act: 1.0469. Min Act: -0.0000

Data Index: 617642 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1482546 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1632623 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 1.0469. Min Range: -1.0469

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1606703 (Python Code)

Max Activating Token Index: 1005

Text #4

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1633620 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1385931 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1519987 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1381415 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1650603 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7992. Min Act: -0.0000

Data Index: 73568 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1570524 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1101265 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1503780 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7909. Min Act: -0.0000

Data Index: 610502 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1368022 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1428405 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1487094 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1590822 (Python Code)

Max Activating Token Index: 965

Text #18

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7672. Min Act: -0.0000

Data Index: 224094 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1362843 (Python Code)

Max Activating Token Index: 591