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

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

Neuron 2786 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1531. Min Range: -4.1531

Max Act: 4.1531. Min Act: -0.0000

Data Index: 561538 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.8201. Min Act: -0.0000

Data Index: 323139 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.8097. Min Act: -0.0000

Data Index: 981291 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.6201. Min Act: -0.0000

Data Index: 816563 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.7919. Min Act: -0.0000

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.5387. Min Act: -0.0000

Data Index: 27031 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.1340. Min Act: -0.0000

Data Index: 613447 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.5059. Min Act: -0.0000

Data Index: 810032 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.2648. Min Act: -0.0000

Data Index: 282744 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.4341. Min Act: -0.0000

Data Index: 674325 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.2667. Min Act: -0.0000

Data Index: 520625 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.2740. Min Act: -0.0000

Data Index: 772175 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 4.1531. Min Range: -4.1531

Max Act: 2.9950. Min Act: -0.0000

Data Index: 1308510 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.2200. Min Act: -0.0000

Data Index: 1103671 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.0220. Min Act: -0.0000

Data Index: 491556 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.0143. Min Act: -0.0000

Data Index: 905149 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.2882. Min Act: -0.0000

Data Index: 1346429 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 4.1531. Min Range: -4.1531

Max Act: 2.7634. Min Act: -0.0000

Data Index: 988327 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 4.1531. Min Range: -4.1531

Max Act: 3.1596. Min Act: -0.0000

Data Index: 2915 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 4.1531. Min Range: -4.1531

Max Act: 2.5647. Min Act: -0.0000

Data Index: 654684 (C4 (Web Text))

Max Activating Token Index: 235