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

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

Neuron 1504 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1235991 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1525513 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3435. Min Act: -0.0000

Data Index: 62360 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3168. Min Act: -0.0000

Data Index: 691712 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1602621 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2994. Min Act: -0.0000

Data Index: 825097 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1520645 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.3119. Min Act: -0.0000

Data Index: 115640 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1309369 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2829. Min Act: -0.0000

Data Index: 415402 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2581. Min Act: -0.0000

Data Index: 271581 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2546. Min Act: -0.0000

Data Index: 863676 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1017148 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2729. Min Act: -0.0000

Data Index: 987118 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2916. Min Act: -0.0000

Data Index: 633977 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2563. Min Act: -0.0000

Data Index: 250297 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1613180 (Python Code)

Max Activating Token Index: 474

Text #17

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1067270 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2549. Min Act: -0.0000

Data Index: 776949 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.4342. Min Range: -0.4342

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1179210 (C4 (Web Text))

Max Activating Token Index: 874