Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 409 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7763. Min Act: -0.1700

Data Index: 1644192 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.8075. Min Act: -0.1700

Data Index: 1605176 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1545310 (Python Code)

Max Activating Token Index: 436

Text #3

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7763. Min Act: -0.1700

Data Index: 1426221 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7138. Min Act: -0.1700

Data Index: 1557638 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1589163 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6825. Min Act: -0.1700

Data Index: 1487052 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6825. Min Act: -0.1700

Data Index: 1526026 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6825. Min Act: -0.1700

Data Index: 1467687 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7450. Min Act: -0.1700

Data Index: 1648620 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.5888. Min Act: -0.1700

Data Index: 1426062 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7138. Min Act: -0.1700

Data Index: 1600332 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.7138. Min Act: -0.1700

Data Index: 1396549 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1617289 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1382193 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1650451 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6200. Min Act: -0.1700

Data Index: 1547035 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.5888. Min Act: -0.1700

Data Index: 1489594 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6513. Min Act: -0.1700

Data Index: 1471268 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 5.8075. Min Range: -5.8075

Max Act: 5.6200. Min Act: -0.1700

Data Index: 1474480 (Python Code)

Max Activating Token Index: 435