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

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

Neuron 995 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: 1.1374. Min Range: -1.1374

Max Act: 1.0223. Min Act: -0.0001

Data Index: 169507 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.1093. Min Act: -0.0001

Data Index: 1113101 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1177136 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0830. Min Act: -0.0001

Data Index: 923849 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0526. Min Act: -0.0001

Data Index: 27689 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0579. Min Act: -0.0001

Data Index: 254313 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0470. Min Act: -0.0001

Data Index: 472054 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0050. Min Act: -0.0001

Data Index: 982102 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.1374. Min Range: -1.1374

Max Act: 1.0177. Min Act: -0.0001

Data Index: 95557 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.9353. Min Act: -0.0001

Data Index: 974380 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.9225. Min Act: -0.0001

Data Index: 398331 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.9020. Min Act: -0.0001

Data Index: 1108876 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.9815. Min Act: -0.0001

Data Index: 774898 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8751. Min Act: -0.0001

Data Index: 445713 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8583. Min Act: -0.0001

Data Index: 264310 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8275. Min Act: -0.0001

Data Index: 62703 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8487. Min Act: -0.0001

Data Index: 1147812 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8499. Min Act: -0.0001

Data Index: 774852 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8766. Min Act: -0.0001

Data Index: 760013 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.1374. Min Range: -1.1374

Max Act: 0.8207. Min Act: -0.0001

Data Index: 816457 (C4 (Web Text))

Max Activating Token Index: 13