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

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

Neuron 1635 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2928. Min Act: -0.0000

Data Index: 1320361 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2969. Min Act: -0.0000

Data Index: 142640 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2731. Min Act: -0.0000

Data Index: 234344 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2664. Min Act: -0.0000

Data Index: 711228 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2488. Min Act: -0.0000

Data Index: 182020 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.2208. Min Act: -0.0000

Data Index: 840718 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0680. Min Act: -0.0000

Data Index: 909763 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1176110 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1298548 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1169004 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0096. Min Act: -0.0000

Data Index: 365743 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1297859 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1251925 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9035. Min Act: -0.0000

Data Index: 930369 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.2969. Min Range: -1.2969

Max Act: 1.0030. Min Act: -0.0000

Data Index: 796067 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1033631 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1173089 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9333. Min Act: -0.0000

Data Index: 667106 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.8687. Min Act: -0.0000

Data Index: 410119 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 1.2969. Min Range: -1.2969

Max Act: 0.9146. Min Act: -0.0000

Data Index: 285250 (C4 (Web Text))

Max Activating Token Index: 492