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

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

Neuron 1247 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: 3.4581. Min Range: -3.4581

Max Act: 3.4267. Min Act: -0.1700

Data Index: 223912 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.4581. Min Act: -0.1700

Data Index: 1214363 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.4424. Min Act: -0.1700

Data Index: 1247123 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.4267. Min Act: -0.1700

Data Index: 1392554 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3954. Min Act: -0.1700

Data Index: 849944 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3954. Min Act: -0.1700

Data Index: 441377 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3797. Min Act: -0.1700

Data Index: 765532 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3797. Min Act: -0.1700

Data Index: 1430771 (Python Code)

Max Activating Token Index: 798

Text #8

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1386838 (Python Code)

Max Activating Token Index: 235

Text #9

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3640. Min Act: -0.1700

Data Index: 1491676 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1591995 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3797. Min Act: -0.1700

Data Index: 1606321 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3640. Min Act: -0.1700

Data Index: 1383484 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3640. Min Act: -0.1700

Data Index: 1503217 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1491645 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 443181 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3326. Min Act: -0.1700

Data Index: 216314 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1523400 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3326. Min Act: -0.1700

Data Index: 1499503 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 3.4581. Min Range: -3.4581

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1472038 (Python Code)

Max Activating Token Index: 73