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

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

Neuron 1012 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1969. Min Act: -0.1700

Data Index: 1454681 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1441207 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1339. Min Act: -0.1700

Data Index: 1640677 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1654. Min Act: -0.1700

Data Index: 1397453 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1480580 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1419513 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1522102 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1529246 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1630779 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1515309 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1642562 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1361370 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1339. Min Act: -0.1700

Data Index: 1473648 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1116706 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1339. Min Act: -0.1700

Data Index: 1430215 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1492703 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1024. Min Act: -0.1700

Data Index: 1505318 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1024. Min Act: -0.1700

Data Index: 1522773 (Python Code)

Max Activating Token Index: 379

Text #18

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1478272 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1024. Min Act: -0.1700

Data Index: 1612315 (Python Code)

Max Activating Token Index: 993