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

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

Neuron 711 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: 3.3001. Min Range: -3.3001

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1363187 (Python Code)

Max Activating Token Index: 470

Text #1

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2345. Min Act: -0.1700

Data Index: 1426139 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1361810 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1652437 (Python Code)

Max Activating Token Index: 1019

Text #4

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.2010. Min Act: -0.1700

Data Index: 1606200 (Python Code)

Max Activating Token Index: 507

Text #5

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1923. Min Act: -0.1700

Data Index: 1491205 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1448024 (Python Code)

Max Activating Token Index: 941

Text #7

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1520815 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1390. Min Act: -0.1700

Data Index: 1573207 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1438. Min Act: -0.1700

Data Index: 1380490 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1472. Min Act: -0.1700

Data Index: 1454675 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1274. Min Act: -0.1700

Data Index: 1448991 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1446317 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1342. Min Act: -0.1700

Data Index: 1576714 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1382. Min Act: -0.1700

Data Index: 1444295 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1215. Min Act: -0.1700

Data Index: 1428975 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1511132 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1092. Min Act: -0.1700

Data Index: 1593300 (Python Code)

Max Activating Token Index: 489

Text #18

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1589883 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 3.3001. Min Range: -3.3001

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1554384 (Python Code)

Max Activating Token Index: 448