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

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

Neuron 1398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.2274. Min Act: -0.0001

Data Index: 1261002 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9852. Min Act: -0.0001

Data Index: 81949 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0191. Min Act: -0.0000

Data Index: 804526 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0440. Min Act: -0.0001

Data Index: 719414 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0165. Min Act: -0.0001

Data Index: 1293242 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8636. Min Act: -0.0001

Data Index: 194269 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8283. Min Act: -0.0001

Data Index: 612597 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8208. Min Act: -0.0001

Data Index: 1567036 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7695. Min Act: -0.0001

Data Index: 1464458 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8105. Min Act: -0.0001

Data Index: 836080 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7962. Min Act: -0.0001

Data Index: 401806 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7172. Min Act: -0.0001

Data Index: 131417 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7040. Min Act: -0.0001

Data Index: 1412962 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1107240 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1537412 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1407675 (Python Code)

Max Activating Token Index: 441

Text #16

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8090. Min Act: -0.0001

Data Index: 578326 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.7834. Min Act: -0.0001

Data Index: 364867 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1579468 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.6740. Min Act: -0.0001

Data Index: 1656401 (Python Code)

Max Activating Token Index: 674