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

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

Neuron 2014 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: 1.9402. Min Range: -1.9402

Max Act: 1.9402. Min Act: -0.0001

Data Index: 241125 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1337051 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8805. Min Act: -0.0000

Data Index: 1056051 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8200. Min Act: -0.0001

Data Index: 131527 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.9001. Min Act: -0.0000

Data Index: 976753 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8916. Min Act: -0.0001

Data Index: 1319584 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.7766. Min Act: -0.0001

Data Index: 131811 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.6823. Min Act: -0.0000

Data Index: 1328898 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.6244. Min Act: -0.0000

Data Index: 269272 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8735. Min Act: -0.0000

Data Index: 1210621 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.6928. Min Act: -0.0000

Data Index: 293440 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.6322. Min Act: -0.0001

Data Index: 605498 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8450. Min Act: -0.0001

Data Index: 1119773 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.8061. Min Act: -0.0001

Data Index: 711161 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.5937. Min Act: -0.0000

Data Index: 1300194 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.5906. Min Act: -0.0001

Data Index: 632103 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1145360 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.5631. Min Act: -0.0001

Data Index: 1163648 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.5727. Min Act: -0.0000

Data Index: 120 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.9402. Min Range: -1.9402

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1149423 (C4 (Web Text))

Max Activating Token Index: 243