Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1584 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.2378. Min Act: -0.1700

Data Index: 1387511 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.1441. Min Act: -0.1700

Data Index: 1654231 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.1441. Min Act: -0.1700

Data Index: 1451191 (Python Code)

Max Activating Token Index: 186

Text #3

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.1128. Min Act: -0.1700

Data Index: 1646623 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.1128. Min Act: -0.1700

Data Index: 1649203 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1504949 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1439588 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1627096 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1489248 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1429641 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.1128. Min Act: -0.1700

Data Index: 1440463 (Python Code)

Max Activating Token Index: 539

Text #11

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1415748 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1532767 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1488043 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0191. Min Act: -0.1700

Data Index: 1583777 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1501131 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1436497 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0503. Min Act: -0.1700

Data Index: 1437487 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 5.2378. Min Range: -5.2378

Max Act: 4.9566. Min Act: -0.1700

Data Index: 1587201 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 5.2378. Min Range: -5.2378

Max Act: 5.0191. Min Act: -0.1700

Data Index: 1432626 (Python Code)

Max Activating Token Index: 394