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

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

Neuron 540 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.3285. Min Act: -0.1700

Data Index: 1506248 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1432298 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.2035. Min Act: -0.1700

Data Index: 1496191 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.2035. Min Act: -0.1700

Data Index: 1454329 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1722. Min Act: -0.1700

Data Index: 1642676 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1097. Min Act: -0.1700

Data Index: 1623611 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0472. Min Act: -0.1700

Data Index: 1393148 (Python Code)

Max Activating Token Index: 691

Text #7

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0160. Min Act: -0.1700

Data Index: 1401114 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0160. Min Act: -0.1700

Data Index: 1548087 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0160. Min Act: -0.1700

Data Index: 1625896 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9535. Min Act: -0.1700

Data Index: 1638496 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9847. Min Act: -0.1700

Data Index: 1547333 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9535. Min Act: -0.1700

Data Index: 1593721 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9847. Min Act: -0.1700

Data Index: 1388181 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9535. Min Act: -0.1700

Data Index: 1613622 (Python Code)

Max Activating Token Index: 244

Text #15

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1602992 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1586517 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1505750 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1426655 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1568251 (Python Code)

Max Activating Token Index: 655