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

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

Neuron 2006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.5363. Min Act: -0.0000

Data Index: 260956 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.8086. Min Act: -0.0000

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.6510. Min Act: -0.0000

Data Index: 1244927 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.6323. Min Act: -0.0000

Data Index: 337722 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.3167. Min Act: -0.0000

Data Index: 742401 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.1332. Min Act: -0.0000

Data Index: 462124 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.7904. Min Act: -0.0000

Data Index: 521186 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.0652. Min Act: -0.0000

Data Index: 971421 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.3387. Min Act: -0.0000

Data Index: 660583 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.0227. Min Act: -0.0000

Data Index: 236887 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.8522. Min Act: -0.0000

Data Index: 1157109 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.9951. Min Act: -0.0000

Data Index: 1120836 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.9889. Min Act: -0.0000

Data Index: 1487057 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.0858. Min Act: -0.0000

Data Index: 138513 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.1074. Min Act: -0.0000

Data Index: 20646 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 3.8086. Min Range: -3.8086

Max Act: 3.0889. Min Act: -0.0000

Data Index: 441873 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.9233. Min Act: -0.0000

Data Index: 679576 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.7577. Min Act: -0.0000

Data Index: 745289 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.7624. Min Act: -0.0000

Data Index: 830868 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.8086. Min Range: -3.8086

Max Act: 2.7716. Min Act: -0.0000

Data Index: 1325245 (C4 (Web Text))

Max Activating Token Index: 280