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

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

Neuron 4987 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3282. Min Range: -2.3282

Max Act: 2.3282. Min Act: -0.0000

Data Index: 1294992 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.3282. Min Range: -2.3282

Max Act: 2.2908. Min Act: -0.0000

Data Index: 56110 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.3282. Min Range: -2.3282

Max Act: 2.1076. Min Act: -0.0000

Data Index: 1331666 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.9818. Min Act: -0.0000

Data Index: 753247 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 2.3282. Min Range: -2.3282

Max Act: 2.0880. Min Act: -0.0000

Data Index: 161525 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.9576. Min Act: -0.0000

Data Index: 822574 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.9028. Min Act: -0.0000

Data Index: 1668 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8984. Min Act: -0.0000

Data Index: 873033 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.9107. Min Act: -0.0000

Data Index: 1147364 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1003380 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8476. Min Act: -0.0000

Data Index: 207851 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8450. Min Act: -0.0000

Data Index: 499756 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.9350. Min Act: -0.0000

Data Index: 389378 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8262. Min Act: -0.0000

Data Index: 509151 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.7050. Min Act: -0.0000

Data Index: 232897 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.7570. Min Act: -0.0000

Data Index: 805048 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.7683. Min Act: -0.0000

Data Index: 687113 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.8604. Min Act: -0.0000

Data Index: 896732 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.7524. Min Act: -0.0000

Data Index: 979580 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 2.3282. Min Range: -2.3282

Max Act: 1.6313. Min Act: -0.0000

Data Index: 889250 (C4 (Web Text))

Max Activating Token Index: 808