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

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

Neuron 5351 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1481423 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.8275. Min Act: -0.0000

Data Index: 537488 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.8293. Min Act: -0.0000

Data Index: 346564 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1385681 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1514684 (Python Code)

Max Activating Token Index: 747

Text #5

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1195956 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7584. Min Act: -0.0000

Data Index: 305101 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1568969 (Python Code)

Max Activating Token Index: 630

Text #8

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1484631 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7219. Min Act: -0.0000

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6684. Min Act: -0.0000

Data Index: 175952 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7078. Min Act: -0.0000

Data Index: 591242 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7042. Min Act: -0.0000

Data Index: 965815 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1363459 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6374. Min Act: -0.0000

Data Index: 121344 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6337. Min Act: -0.0000

Data Index: 775041 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1632225 (Python Code)

Max Activating Token Index: 687

Text #17

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6517. Min Act: -0.0000

Data Index: 716368 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6269. Min Act: -0.0000

Data Index: 610837 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.8293. Min Range: -0.8293

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1593328 (Python Code)

Max Activating Token Index: 168