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

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

Neuron 4404 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: 1.7897. Min Range: -1.7897

Max Act: 1.7897. Min Act: -0.0000

Data Index: 1393958 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1362759 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.6815. Min Act: -0.0000

Data Index: 1402547 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1360081 (Python Code)

Max Activating Token Index: 778

Text #4

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1587548 (Python Code)

Max Activating Token Index: 543

Text #5

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1500956 (Python Code)

Max Activating Token Index: 459

Text #6

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.1115. Min Act: -0.0000

Data Index: 1544264 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1476092 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 1.7897. Min Range: -1.7897

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1383791 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1362664 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1517867 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1583828 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1646516 (Python Code)

Max Activating Token Index: 588

Text #13

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1596541 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1566029 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1492370 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1412295 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1459045 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1574981 (Python Code)

Max Activating Token Index: 554

Text #19

Max Range: 1.7897. Min Range: -1.7897

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1583362 (Python Code)

Max Activating Token Index: 430