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

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

Neuron 1571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.9155. Min Act: 0.0002

Data Index: 492167 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8369. Min Act: -0.0000

Data Index: 300742 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7734. Min Act: -0.0000

Data Index: 430392 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7273. Min Act: -0.0000

Data Index: 170862 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.5504. Min Act: 0.0000

Data Index: 741714 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.4746. Min Act: -0.0000

Data Index: 1086331 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7188. Min Act: -0.0000

Data Index: 408793 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.3886. Min Act: 0.0002

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.3035. Min Act: -0.0000

Data Index: 415687 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.3525. Min Act: 0.0000

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.2402. Min Act: 0.0000

Data Index: 606792 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.4958. Min Act: -0.0000

Data Index: 1300856 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.1437. Min Act: -0.0001

Data Index: 1343502 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.1822. Min Act: -0.0000

Data Index: 195078 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.2270. Min Act: -0.0000

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.9155. Min Range: -3.9155

Max Act: 2.4389. Min Act: -0.0000

Data Index: 396272 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.1475. Min Act: -0.0001

Data Index: 637326 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.9155. Min Range: -3.9155

Max Act: 2.9861. Min Act: 0.0002

Data Index: 768935 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 3.9155. Min Range: -3.9155

Max Act: 2.9891. Min Act: -0.0000

Data Index: 215562 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.9155. Min Range: -3.9155

Max Act: 2.7119. Min Act: -0.0000

Data Index: 1019427 (C4 (Web Text))

Max Activating Token Index: 906