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

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

Neuron 4472 in Layer 0

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: 1.9212. Min Range: -1.9212

Max Act: 1.9212. Min Act: -0.0001

Data Index: 1435281 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.8543. Min Act: -0.0001

Data Index: 1573086 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.8154. Min Act: -0.0001

Data Index: 1472886 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7905. Min Act: -0.0001

Data Index: 1481642 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7856. Min Act: -0.0001

Data Index: 1574742 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7567. Min Act: -0.0001

Data Index: 1563754 (Python Code)

Max Activating Token Index: 411

Text #6

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7314. Min Act: -0.0001

Data Index: 1625797 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7297. Min Act: -0.0001

Data Index: 1544450 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6976. Min Act: -0.0001

Data Index: 1365543 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6748. Min Act: -0.0001

Data Index: 1599574 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6804. Min Act: -0.0001

Data Index: 1600747 (Python Code)

Max Activating Token Index: 625

Text #11

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6361. Min Act: -0.0001

Data Index: 1641759 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5888. Min Act: -0.0001

Data Index: 1604779 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5855. Min Act: -0.0001

Data Index: 1546347 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5789. Min Act: -0.0002

Data Index: 1438788 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6163. Min Act: -0.0001

Data Index: 1610819 (Python Code)

Max Activating Token Index: 345

Text #16

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5772. Min Act: -0.0001

Data Index: 1538165 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5506. Min Act: -0.0001

Data Index: 1589905 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5572. Min Act: -0.0001

Data Index: 1502322 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5593. Min Act: -0.0001

Data Index: 1447151 (Python Code)

Max Activating Token Index: 1023