Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3053. Min Range: -1.3053

Max Act: 1.3053. Min Act: -0.0001

Data Index: 1013944 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.3053. Min Range: -1.3053

Max Act: 1.0977. Min Act: -0.0001

Data Index: 1152454 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8939. Min Act: -0.0001

Data Index: 874011 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8972. Min Act: -0.0001

Data Index: 857846 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7570. Min Act: -0.0001

Data Index: 1260509 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1222969 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7723. Min Act: -0.0001

Data Index: 472032 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8436. Min Act: -0.0001

Data Index: 232395 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8093. Min Act: -0.0001

Data Index: 262762 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.6905. Min Act: -0.0001

Data Index: 5562 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7923. Min Act: -0.0001

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.8030. Min Act: -0.0001

Data Index: 674402 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7041. Min Act: -0.0001

Data Index: 490148 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7423. Min Act: -0.0001

Data Index: 220021 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7389. Min Act: -0.0001

Data Index: 549918 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1084977 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7004. Min Act: -0.0001

Data Index: 390152 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.6895. Min Act: -0.0001

Data Index: 23088 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7193. Min Act: -0.0001

Data Index: 241790 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.3053. Min Range: -1.3053

Max Act: 0.7773. Min Act: -0.0001

Data Index: 1019211 (C4 (Web Text))

Max Activating Token Index: 171