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

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

Neuron 829 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.5886. Min Act: -0.0001

Data Index: 1372270 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.6315. Min Act: -0.0001

Data Index: 1656719 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4931. Min Act: -0.0001

Data Index: 1481533 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4492. Min Act: -0.0001

Data Index: 1484457 (Python Code)

Max Activating Token Index: 488

Text #4

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4601. Min Act: -0.0001

Data Index: 1522558 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2695. Min Act: -0.0001

Data Index: 1559789 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3231. Min Act: -0.0001

Data Index: 1593275 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3538. Min Act: -0.0001

Data Index: 1636459 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.4737. Min Act: -0.0001

Data Index: 1545014 (Python Code)

Max Activating Token Index: 890

Text #9

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3089. Min Act: -0.0001

Data Index: 1473847 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2556. Min Act: -0.0001

Data Index: 1469242 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1538836 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2872. Min Act: -0.0001

Data Index: 1378548 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2526. Min Act: -0.0001

Data Index: 1586275 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2430. Min Act: -0.0001

Data Index: 1577539 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2395. Min Act: -0.0001

Data Index: 1537161 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2388. Min Act: -0.0001

Data Index: 1563676 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2626. Min Act: -0.0001

Data Index: 1457965 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1561901 (Python Code)

Max Activating Token Index: 652

Text #19

Max Range: 1.6315. Min Range: -1.6315

Max Act: 1.2930. Min Act: -0.0001

Data Index: 1489282 (Python Code)

Max Activating Token Index: 546