Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1750 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1415509 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.1459. Min Act: -0.1700

Data Index: 1386186 (Python Code)

Max Activating Token Index: 407

Text #2

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.1462. Min Act: -0.1700

Data Index: 1596809 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.1186. Min Act: -0.1700

Data Index: 1369011 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.1095. Min Act: -0.1699

Data Index: 1458589 (Python Code)

Max Activating Token Index: 376

Text #5

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1472284 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0721. Min Act: -0.1695

Data Index: 1507554 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0549. Min Act: -0.1700

Data Index: 1524948 (Python Code)

Max Activating Token Index: 446

Text #8

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0586. Min Act: -0.1700

Data Index: 127070 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0481. Min Act: -0.1699

Data Index: 1381117 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0455. Min Act: -0.1699

Data Index: 1548688 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0419. Min Act: -0.1700

Data Index: 1506768 (Python Code)

Max Activating Token Index: 436

Text #12

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0120. Min Act: -0.1700

Data Index: 1027338 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0438. Min Act: -0.1700

Data Index: 1587328 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0425. Min Act: -0.1700

Data Index: 1289710 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1492121 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 3.2095. Min Range: -3.2095

Max Act: 2.9865. Min Act: -0.1700

Data Index: 1644350 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0213. Min Act: -0.1629

Data Index: 345006 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 3.2095. Min Range: -3.2095

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1037882 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 3.2095. Min Range: -3.2095

Max Act: 2.9929. Min Act: -0.1700

Data Index: 311308 (C4 (Web Text))

Max Activating Token Index: 97