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

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

Neuron 5069 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0473. Min Range: -2.0473

Max Act: 2.0473. Min Act: -0.0000

Data Index: 423835 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8478. Min Act: -0.0000

Data Index: 1078745 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8442. Min Act: -0.0000

Data Index: 548634 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8626. Min Act: -0.0000

Data Index: 1064089 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8377. Min Act: -0.0000

Data Index: 623555 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7913. Min Act: -0.0000

Data Index: 692949 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7845. Min Act: -0.0000

Data Index: 233099 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7232. Min Act: -0.0000

Data Index: 210866 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7827. Min Act: -0.0000

Data Index: 200586 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7775. Min Act: -0.0000

Data Index: 35405 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7714. Min Act: -0.0000

Data Index: 825308 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1274443 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7502. Min Act: -0.0000

Data Index: 280748 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8051. Min Act: -0.0000

Data Index: 1293643 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.8389. Min Act: -0.0000

Data Index: 103591 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1036285 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7353. Min Act: -0.0000

Data Index: 1072159 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1188693 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 2.0473. Min Range: -2.0473

Max Act: 1.7699. Min Act: -0.0000

Data Index: 259668 (C4 (Web Text))

Max Activating Token Index: 943