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

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

Neuron 1083 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7875. Min Act: -0.0001

Data Index: 412885 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7636. Min Act: -0.0001

Data Index: 553978 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1246504 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.7405. Min Act: -0.0001

Data Index: 93078 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6544. Min Act: -0.0001

Data Index: 306300 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.6260. Min Act: -0.0001

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5696. Min Act: -0.0001

Data Index: 1237706 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5729. Min Act: -0.0001

Data Index: 674240 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5329. Min Act: -0.0001

Data Index: 987499 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5318. Min Act: -0.0001

Data Index: 1026883 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5775. Min Act: -0.0001

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5536. Min Act: -0.0001

Data Index: 183511 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5672. Min Act: -0.0001

Data Index: 1027784 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5362. Min Act: -0.0001

Data Index: 132043 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5674. Min Act: -0.0001

Data Index: 106739 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1267046 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5605. Min Act: -0.0001

Data Index: 701277 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5383. Min Act: -0.0001

Data Index: 5493 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.7875. Min Range: -0.7875

Max Act: 0.5790. Min Act: -0.0001

Data Index: 792987 (C4 (Web Text))

Max Activating Token Index: 737