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

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

Neuron 5104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.1236. Min Act: -0.0002

Data Index: 1637049 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0969. Min Act: -0.0002

Data Index: 1544537 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.1061. Min Act: -0.0002

Data Index: 1483266 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0879. Min Act: -0.0002

Data Index: 1564136 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0541. Min Act: -0.0002

Data Index: 1386106 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0723. Min Act: -0.0002

Data Index: 1594156 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0438. Min Act: -0.0002

Data Index: 1399952 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0685. Min Act: -0.0002

Data Index: 1518376 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0550. Min Act: -0.0002

Data Index: 1401077 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0013. Min Act: -0.0002

Data Index: 1436368 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0124. Min Act: -0.0002

Data Index: 1566952 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 1.1236. Min Range: -1.1236

Max Act: 0.9997. Min Act: -0.0002

Data Index: 1381380 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0503. Min Act: -0.0002

Data Index: 1518700 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0216. Min Act: -0.0002

Data Index: 1557041 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0076. Min Act: -0.0002

Data Index: 1510397 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0009. Min Act: -0.0002

Data Index: 1508217 (Python Code)

Max Activating Token Index: 521

Text #16

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0023. Min Act: -0.0002

Data Index: 1621013 (Python Code)

Max Activating Token Index: 385

Text #17

Max Range: 1.1236. Min Range: -1.1236

Max Act: 0.9909. Min Act: -0.0002

Data Index: 1482364 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.1236. Min Range: -1.1236

Max Act: 0.9967. Min Act: -0.0002

Data Index: 1499198 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 1.1236. Min Range: -1.1236

Max Act: 1.0155. Min Act: -0.0002

Data Index: 1499670 (Python Code)

Max Activating Token Index: 580