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

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

Neuron 3919 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1197334 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1537472 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1484623 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1575529 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1520894 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1430561 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1911. Min Act: -0.0000

Data Index: 658563 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1471. Min Act: -0.0000

Data Index: 59106 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1584104 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1067. Min Act: -0.0000

Data Index: 917013 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1626592 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1174. Min Act: -0.0000

Data Index: 1410688 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1573721 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0758. Min Act: -0.0000

Data Index: 358572 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1575749 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1612650 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1504314 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1174972 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1458139 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 1.7012. Min Range: -1.7012

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1605204 (Python Code)

Max Activating Token Index: 372