Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1377. Min Range: -1.1377

Max Act: 1.1377. Min Act: -0.0001

Data Index: 1186189 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.1377. Min Range: -1.1377

Max Act: 1.0807. Min Act: -0.0001

Data Index: 990177 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.9428. Min Act: -0.0000

Data Index: 720260 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8950. Min Act: -0.0001

Data Index: 238348 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8685. Min Act: -0.0001

Data Index: 228025 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8376. Min Act: -0.0001

Data Index: 916775 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8633. Min Act: -0.0001

Data Index: 19466 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8068. Min Act: -0.0000

Data Index: 908882 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.8066. Min Act: -0.0001

Data Index: 1537072 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1253145 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7821. Min Act: -0.0001

Data Index: 1168321 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7526. Min Act: -0.0001

Data Index: 656540 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1023124 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7780. Min Act: -0.0001

Data Index: 123633 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1411960 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7360. Min Act: -0.0001

Data Index: 460454 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1460799 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7063. Min Act: -0.0001

Data Index: 387126 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7523. Min Act: -0.0001

Data Index: 796260 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.1377. Min Range: -1.1377

Max Act: 0.7147. Min Act: -0.0001

Data Index: 1071627 (C4 (Web Text))

Max Activating Token Index: 259