Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0134. Min Range: -5.0134

Max Act: 5.0134. Min Act: -0.1700

Data Index: 1573208 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.9509. Min Act: -0.1699

Data Index: 1362467 (Python Code)

Max Activating Token Index: 610

Text #2

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.9196. Min Act: -0.1700

Data Index: 1650154 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.8884. Min Act: -0.1699

Data Index: 1406634 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.8571. Min Act: -0.1700

Data Index: 1380233 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.7321. Min Act: -0.1700

Data Index: 1398344 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.7009. Min Act: -0.1700

Data Index: 1570228 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.7321. Min Act: -0.1700

Data Index: 1395063 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1515618 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.6384. Min Act: -0.1700

Data Index: 1586084 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.6071. Min Act: -0.1700

Data Index: 1518522 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.6696. Min Act: -0.1700

Data Index: 1531787 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.6384. Min Act: -0.1700

Data Index: 1650203 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.5759. Min Act: -0.1700

Data Index: 1408545 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.5446. Min Act: -0.1700

Data Index: 1652229 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.5446. Min Act: -0.1700

Data Index: 1601146 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.5759. Min Act: -0.1700

Data Index: 1645823 (Python Code)

Max Activating Token Index: 379

Text #17

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.4821. Min Act: -0.1700

Data Index: 1569253 (Python Code)

Max Activating Token Index: 358

Text #18

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.4509. Min Act: -0.1700

Data Index: 1601918 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 5.0134. Min Range: -5.0134

Max Act: 4.4821. Min Act: -0.1700

Data Index: 1547852 (Python Code)

Max Activating Token Index: 914