Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1624 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1376450 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1545611 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1387385 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4952. Min Act: -0.1700

Data Index: 1475548 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5577. Min Act: -0.1700

Data Index: 1362931 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.6202. Min Act: -0.1700

Data Index: 1397264 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1540347 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.6202. Min Act: -0.1700

Data Index: 1375909 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.6202. Min Act: -0.1700

Data Index: 1485489 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5889. Min Act: -0.1700

Data Index: 1643927 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4639. Min Act: -0.1700

Data Index: 1632836 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5577. Min Act: -0.1700

Data Index: 1433952 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1471319 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1365470 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4952. Min Act: -0.1700

Data Index: 1379427 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4639. Min Act: -0.1700

Data Index: 1390613 (Python Code)

Max Activating Token Index: 909

Text #16

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4952. Min Act: -0.1700

Data Index: 1574688 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.5264. Min Act: -0.1700

Data Index: 1521352 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.3702. Min Act: -0.1700

Data Index: 1380473 (Python Code)

Max Activating Token Index: 497

Text #19

Max Range: 5.6202. Min Range: -5.6202

Max Act: 5.4639. Min Act: -0.1699

Data Index: 1489884 (Python Code)

Max Activating Token Index: 284