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

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

Neuron 1117 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: 3.4739. Min Range: -3.4739

Max Act: 3.4739. Min Act: -0.1699

Data Index: 1465722 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4582. Min Act: -0.1700

Data Index: 1408537 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4582. Min Act: -0.1699

Data Index: 1631161 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4268. Min Act: -0.1700

Data Index: 1575014 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.4112. Min Act: -0.1699

Data Index: 1518651 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3798. Min Act: -0.1699

Data Index: 1367842 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3641. Min Act: -0.1699

Data Index: 1654320 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3484. Min Act: -0.1700

Data Index: 1468370 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3484. Min Act: -0.1700

Data Index: 1396593 (Python Code)

Max Activating Token Index: 500

Text #9

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3327. Min Act: -0.1696

Data Index: 1536420 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3013. Min Act: -0.1700

Data Index: 1619591 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3013. Min Act: -0.1700

Data Index: 1369338 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.3170. Min Act: -0.1700

Data Index: 1361988 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2856. Min Act: -0.1700

Data Index: 1413264 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2856. Min Act: -0.1700

Data Index: 1417736 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1420850 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1604122 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1551545 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2542. Min Act: -0.1700

Data Index: 1626128 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 3.4739. Min Range: -3.4739

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1513264 (Python Code)

Max Activating Token Index: 835