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

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

Neuron 459 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: 0.3879. Min Range: -0.3879

Max Act: 0.3578. Min Act: -0.0001

Data Index: 734984 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3879. Min Act: -0.0001

Data Index: 1204171 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1050352 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3147. Min Act: -0.0001

Data Index: 883320 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3339. Min Act: -0.0001

Data Index: 401183 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3088. Min Act: -0.0001

Data Index: 1183470 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2979. Min Act: -0.0001

Data Index: 50673 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3017. Min Act: -0.0001

Data Index: 715341 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3088. Min Act: -0.0001

Data Index: 535462 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3071. Min Act: -0.0001

Data Index: 221866 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3107. Min Act: -0.0001

Data Index: 416907 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2579. Min Act: -0.0001

Data Index: 710332 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2896. Min Act: -0.0001

Data Index: 1282647 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2623. Min Act: -0.0001

Data Index: 1292654 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2930. Min Act: -0.0001

Data Index: 1272339 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3057. Min Act: -0.0000

Data Index: 465090 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1232075 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2931. Min Act: -0.0001

Data Index: 544467 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.3025. Min Act: -0.0001

Data Index: 480779 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.3879. Min Range: -0.3879

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1080815 (C4 (Web Text))

Max Activating Token Index: 296