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

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

Neuron 1422 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: 3.5562. Min Range: -3.5562

Max Act: 3.5562. Min Act: -0.0000

Data Index: 721774 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.2985. Min Act: -0.0000

Data Index: 1578262 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.2499. Min Act: -0.0000

Data Index: 1308233 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3394. Min Act: -0.0000

Data Index: 838265 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.4792. Min Act: -0.0000

Data Index: 405182 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.0960. Min Act: -0.0000

Data Index: 1601577 (Python Code)

Max Activating Token Index: 111

Text #6

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.0805. Min Act: -0.0000

Data Index: 1625309 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.0390. Min Act: -0.0000

Data Index: 1638211 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.1638. Min Act: -0.0000

Data Index: 1416879 (Python Code)

Max Activating Token Index: 803

Text #9

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.1557. Min Act: -0.0000

Data Index: 1377149 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.9739. Min Act: -0.0000

Data Index: 1485028 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.6956. Min Act: -0.0000

Data Index: 1498732 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.9592. Min Act: -0.0000

Data Index: 571153 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8080. Min Act: -0.0000

Data Index: 1481118 (Python Code)

Max Activating Token Index: 490

Text #14

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.0410. Min Act: -0.0000

Data Index: 1527505 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.9143. Min Act: -0.0000

Data Index: 1588692 (Python Code)

Max Activating Token Index: 115

Text #16

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8605. Min Act: -0.0000

Data Index: 1624719 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8501. Min Act: -0.0000

Data Index: 893358 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8333. Min Act: -0.0000

Data Index: 1011868 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 3.5562. Min Range: -3.5562

Max Act: 2.8337. Min Act: -0.0000

Data Index: 338167 (C4 (Web Text))

Max Activating Token Index: 40