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

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

Neuron 3537 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3921. Min Act: -0.0002

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3548. Min Act: -0.0001

Data Index: 688025 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3083. Min Act: -0.0001

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3137. Min Act: -0.0001

Data Index: 225212 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2949. Min Act: -0.0001

Data Index: 235676 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3027. Min Act: -0.0001

Data Index: 958185 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3001. Min Act: -0.0002

Data Index: 1325328 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3008. Min Act: -0.0001

Data Index: 1355764 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2674. Min Act: -0.0001

Data Index: 201334 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1235415 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1260684 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2814. Min Act: -0.0001

Data Index: 113461 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2816. Min Act: -0.0001

Data Index: 5303 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.3044. Min Act: -0.0002

Data Index: 665292 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2799. Min Act: -0.0001

Data Index: 57514 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2896. Min Act: -0.0001

Data Index: 918545 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2802. Min Act: -0.0002

Data Index: 956810 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2335. Min Act: -0.0001

Data Index: 849013 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1325733 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.3921. Min Range: -0.3921

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1315991 (C4 (Web Text))

Max Activating Token Index: 565