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

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

Neuron 832 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0139. Min Range: -2.0139

Max Act: 2.0139. Min Act: -0.0000

Data Index: 696483 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.8795. Min Act: -0.0000

Data Index: 313862 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.8388. Min Act: -0.0000

Data Index: 302309 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7820. Min Act: -0.0000

Data Index: 11726 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7246. Min Act: -0.0000

Data Index: 490761 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.8734. Min Act: -0.0000

Data Index: 658687 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7982. Min Act: -0.0000

Data Index: 885391 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7482. Min Act: -0.0000

Data Index: 1147691 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7987. Min Act: -0.0000

Data Index: 375724 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.8388. Min Act: -0.0000

Data Index: 245275 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7995. Min Act: -0.0000

Data Index: 589759 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7565. Min Act: -0.0000

Data Index: 1012825 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7978. Min Act: -0.0000

Data Index: 1221949 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1081749 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7838. Min Act: -0.0000

Data Index: 939444 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.6856. Min Act: -0.0000

Data Index: 189399 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1282535 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.7142. Min Act: -0.0000

Data Index: 281569 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.6701. Min Act: -0.0000

Data Index: 313357 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 2.0139. Min Range: -2.0139

Max Act: 1.6797. Min Act: -0.0000

Data Index: 661857 (C4 (Web Text))

Max Activating Token Index: 824