Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3173. Min Act: -0.0001

Data Index: 610616 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1100409 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3243. Min Act: -0.0001

Data Index: 673013 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3032. Min Act: -0.0001

Data Index: 666187 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2976. Min Act: -0.0001

Data Index: 138613 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1050483 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3057. Min Act: -0.0001

Data Index: 609969 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3026. Min Act: -0.0001

Data Index: 39915 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3031. Min Act: -0.0001

Data Index: 574619 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3000. Min Act: -0.0001

Data Index: 306048 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3092. Min Act: -0.0001

Data Index: 1023330 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2966. Min Act: -0.0001

Data Index: 290869 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2851. Min Act: -0.0001

Data Index: 1130464 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3039. Min Act: -0.0001

Data Index: 918167 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.3017. Min Act: -0.0001

Data Index: 397116 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2760. Min Act: -0.0001

Data Index: 838863 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2857. Min Act: -0.0001

Data Index: 155061 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2911. Min Act: -0.0001

Data Index: 1107936 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2801. Min Act: -0.0001

Data Index: 194974 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.3341. Min Range: -0.3341

Max Act: 0.2800. Min Act: -0.0001

Data Index: 499089 (C4 (Web Text))

Max Activating Token Index: 960