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

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

Neuron 1653 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9487. Min Range: -1.9487

Max Act: 1.9487. Min Act: -0.0000

Data Index: 132027 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.9487. Min Range: -1.9487

Max Act: 1.0799. Min Act: -0.0000

Data Index: 806329 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.9487. Min Range: -1.9487

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1071855 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1568992 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 1.9487. Min Range: -1.9487

Max Act: 1.0166. Min Act: -0.0000

Data Index: 412618 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9840. Min Act: 0.0001

Data Index: 1460958 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1210088 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9010. Min Act: -0.0000

Data Index: 204472 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9326. Min Act: -0.0000

Data Index: 855616 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9726. Min Act: -0.0000

Data Index: 479797 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1565536 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1617772 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8363. Min Act: -0.0000

Data Index: 370817 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.9049. Min Act: 0.0000

Data Index: 416341 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.9487. Min Range: -1.9487

Max Act: 1.0112. Min Act: -0.0000

Data Index: 183989 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1594443 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8546. Min Act: 0.0000

Data Index: 1504037 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1401076 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8275. Min Act: 0.0000

Data Index: 1654166 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 1.9487. Min Range: -1.9487

Max Act: 0.8652. Min Act: -0.0000

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 1002