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

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

Neuron 222 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.9693. Min Act: -0.1700

Data Index: 1370457 (Python Code)

Max Activating Token Index: 269

Text #1

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.9068. Min Act: -0.1700

Data Index: 1562272 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.9068. Min Act: -0.1700

Data Index: 1435202 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8755. Min Act: -0.1700

Data Index: 1463480 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8755. Min Act: -0.1700

Data Index: 1393917 (Python Code)

Max Activating Token Index: 391

Text #5

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.9380. Min Act: -0.1700

Data Index: 1608980 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8755. Min Act: -0.1700

Data Index: 1366965 (Python Code)

Max Activating Token Index: 335

Text #7

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8443. Min Act: -0.1700

Data Index: 1368707 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8443. Min Act: -0.1700

Data Index: 1566569 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8130. Min Act: -0.1700

Data Index: 1457659 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7818. Min Act: -0.1700

Data Index: 1599405 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8443. Min Act: -0.1700

Data Index: 1382224 (Python Code)

Max Activating Token Index: 262

Text #12

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8443. Min Act: -0.1700

Data Index: 1451247 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8130. Min Act: -0.1700

Data Index: 1471269 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.8443. Min Act: -0.1700

Data Index: 1579123 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7505. Min Act: -0.1700

Data Index: 1433856 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7818. Min Act: -0.1700

Data Index: 1558024 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7818. Min Act: -0.1700

Data Index: 1547218 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7818. Min Act: -0.1700

Data Index: 1394610 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 5.9693. Min Range: -5.9693

Max Act: 5.7505. Min Act: -0.1700

Data Index: 1445731 (Python Code)

Max Activating Token Index: 155