Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1380 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1537720 (Python Code)

Max Activating Token Index: 360

Text #1

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5572. Min Act: -0.1700

Data Index: 1525868 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5572. Min Act: -0.1700

Data Index: 1591211 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.6353. Min Act: -0.1700

Data Index: 1407601 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.6041. Min Act: -0.1700

Data Index: 1628991 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5416. Min Act: -0.1700

Data Index: 1603970 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5572. Min Act: -0.1700

Data Index: 1639022 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5103. Min Act: -0.1700

Data Index: 1369637 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4791. Min Act: -0.1700

Data Index: 1408094 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5103. Min Act: -0.1699

Data Index: 1560419 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5103. Min Act: -0.1700

Data Index: 1585110 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5260. Min Act: -0.1700

Data Index: 1422757 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4947. Min Act: -0.1700

Data Index: 1376044 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5416. Min Act: -0.1700

Data Index: 1434706 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5260. Min Act: -0.1700

Data Index: 1526211 (Python Code)

Max Activating Token Index: 477

Text #15

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4635. Min Act: -0.1700

Data Index: 1555921 (Python Code)

Max Activating Token Index: 269

Text #16

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4947. Min Act: -0.1700

Data Index: 1497179 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4635. Min Act: -0.1700

Data Index: 1361336 (Python Code)

Max Activating Token Index: 752

Text #18

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.5103. Min Act: -0.1700

Data Index: 1404695 (Python Code)

Max Activating Token Index: 259

Text #19

Max Range: 5.6978. Min Range: -5.6978

Max Act: 5.4947. Min Act: -0.1700

Data Index: 1419340 (Python Code)

Max Activating Token Index: 271