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

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

Neuron 178 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.7796. Min Act: 0.1138

Data Index: 1594282 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.7483. Min Act: -0.1518

Data Index: 1576914 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.7170. Min Act: -0.1136

Data Index: 1647608 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.6700. Min Act: -0.1615

Data Index: 1643805 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5448. Min Act: -0.0940

Data Index: 1367224 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5291. Min Act: -0.1054

Data Index: 1445490 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5291. Min Act: -0.0956

Data Index: 1466871 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.5291. Min Act: -0.1412

Data Index: 1411055 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4821. Min Act: -0.0513

Data Index: 1538878 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4821. Min Act: -0.1687

Data Index: 1360792 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4821. Min Act: -0.1686

Data Index: 1644504 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4194. Min Act: -0.0796

Data Index: 1612305 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4194. Min Act: -0.0578

Data Index: 1627988 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4037. Min Act: -0.1567

Data Index: 1656337 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.4037. Min Act: -0.1389

Data Index: 1434334 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.3881. Min Act: -0.1317

Data Index: 1600979 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.3724. Min Act: -0.1636

Data Index: 1450205 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.3410. Min Act: -0.1208

Data Index: 1654202 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.3410. Min Act: -0.1378

Data Index: 1462360 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 3.7796. Min Range: -3.7796

Max Act: 3.3567. Min Act: -0.1099

Data Index: 1508831 (Python Code)

Max Activating Token Index: 725