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

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

Neuron 3435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5425. Min Act: -0.0000

Data Index: 378347 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5359. Min Act: -0.0000

Data Index: 434208 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4958. Min Act: -0.0000

Data Index: 883554 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4921. Min Act: -0.0000

Data Index: 17543 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4999. Min Act: -0.0000

Data Index: 474666 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4917. Min Act: -0.0000

Data Index: 847150 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5104. Min Act: -0.0000

Data Index: 638252 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1203601 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4878. Min Act: -0.0000

Data Index: 261513 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4789. Min Act: -0.0000

Data Index: 956435 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4570. Min Act: -0.0000

Data Index: 807768 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4836. Min Act: -0.0000

Data Index: 157433 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4538. Min Act: -0.0000

Data Index: 382088 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4662. Min Act: -0.0000

Data Index: 856912 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4480. Min Act: -0.0000

Data Index: 44850 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1305603 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1206374 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4607. Min Act: -0.0000

Data Index: 913890 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4571. Min Act: -0.0000

Data Index: 489046 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4396. Min Act: -0.0000

Data Index: 787634 (C4 (Web Text))

Max Activating Token Index: 92