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

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

Neuron 1440 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2136. Min Range: -5.2136

Max Act: 5.2136. Min Act: -0.1700

Data Index: 1444126 (Python Code)

Max Activating Token Index: 126

Text #1

Max Range: 5.2136. Min Range: -5.2136

Max Act: 5.2136. Min Act: -0.1700

Data Index: 1522871 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 5.2136. Min Range: -5.2136

Max Act: 5.1511. Min Act: -0.1697

Data Index: 1627180 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 1385186 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 1572827 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 135896 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 1370015 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 381437 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9011. Min Act: -0.1700

Data Index: 1551047 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9323. Min Act: -0.1700

Data Index: 1384957 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8698. Min Act: -0.1700

Data Index: 1391836 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8698. Min Act: -0.1700

Data Index: 1614358 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8073. Min Act: -0.1700

Data Index: 1605882 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9011. Min Act: -0.1699

Data Index: 1513529 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8386. Min Act: -0.1700

Data Index: 1590444 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.9011. Min Act: -0.1699

Data Index: 1508582 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8073. Min Act: -0.1700

Data Index: 831348 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8073. Min Act: -0.1700

Data Index: 1497451 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8698. Min Act: -0.1700

Data Index: 1393088 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 5.2136. Min Range: -5.2136

Max Act: 4.8073. Min Act: -0.1700

Data Index: 1384397 (Python Code)

Max Activating Token Index: 720