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

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

Neuron 2225 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: 0.4608. Min Range: -0.4608

Max Act: 0.4608. Min Act: -0.0001

Data Index: 758363 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3779. Min Act: -0.0001

Data Index: 522619 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3264. Min Act: -0.0001

Data Index: 772982 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3168. Min Act: -0.0001

Data Index: 648821 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3338. Min Act: -0.0001

Data Index: 208915 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1283045 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3494. Min Act: -0.0001

Data Index: 775467 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3050. Min Act: -0.0001

Data Index: 1290748 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3294. Min Act: -0.0001

Data Index: 230647 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1474983 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2952. Min Act: -0.0001

Data Index: 923775 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2797. Min Act: -0.0001

Data Index: 853778 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3262. Min Act: -0.0001

Data Index: 674742 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1157316 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1097130 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2823. Min Act: -0.0001

Data Index: 672787 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2663. Min Act: -0.0001

Data Index: 9174 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2710. Min Act: -0.0001

Data Index: 1560736 (Python Code)

Max Activating Token Index: 949

Text #18

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1618761 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1417636 (Python Code)

Max Activating Token Index: 948