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

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

Neuron 1675 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: 3.3983. Min Range: -3.3983

Max Act: 3.3983. Min Act: -0.1700

Data Index: 1363363 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3826. Min Act: -0.1700

Data Index: 1482073 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3669. Min Act: -0.1700

Data Index: 1552352 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3826. Min Act: -0.1700

Data Index: 1393019 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3512. Min Act: -0.1700

Data Index: 1479515 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3198. Min Act: -0.1700

Data Index: 1612685 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.3041. Min Act: -0.1700

Data Index: 1428574 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1636179 (Python Code)

Max Activating Token Index: 76

Text #8

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1374940 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2884. Min Act: -0.1700

Data Index: 1583340 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2570. Min Act: -0.1700

Data Index: 1395375 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2570. Min Act: -0.1700

Data Index: 1494018 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2413. Min Act: -0.1700

Data Index: 1615716 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.1941. Min Act: -0.1700

Data Index: 1486733 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2256. Min Act: -0.1700

Data Index: 1655367 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2413. Min Act: -0.1700

Data Index: 1566797 (Python Code)

Max Activating Token Index: 519

Text #16

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2256. Min Act: -0.1700

Data Index: 1650205 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2570. Min Act: -0.1700

Data Index: 1425316 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2256. Min Act: -0.1700

Data Index: 1442310 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 3.3983. Min Range: -3.3983

Max Act: 3.2727. Min Act: -0.1700

Data Index: 1590223 (Python Code)

Max Activating Token Index: 906