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

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

Neuron 88 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3496. Min Act: -0.0001

Data Index: 1180272 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1171504 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3016. Min Act: -0.0001

Data Index: 305582 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3187. Min Act: -0.0001

Data Index: 90006 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3026. Min Act: 0.0000

Data Index: 333733 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2616. Min Act: -0.0001

Data Index: 732800 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3050. Min Act: 0.0000

Data Index: 740633 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2899. Min Act: -0.0000

Data Index: 533578 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2871. Min Act: -0.0000

Data Index: 739404 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3078. Min Act: -0.0001

Data Index: 85013 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1242885 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2813. Min Act: -0.0001

Data Index: 266078 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2908. Min Act: -0.0001

Data Index: 763223 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1177996 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1139438 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3081. Min Act: -0.0000

Data Index: 719624 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1142829 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2859. Min Act: -0.0001

Data Index: 980935 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1000303 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.3496. Min Range: -0.3496

Max Act: 0.2817. Min Act: 0.0000

Data Index: 445328 (C4 (Web Text))

Max Activating Token Index: 46