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

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

Neuron 1671 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: 5.1902. Min Range: -5.1902

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1649882 (Python Code)

Max Activating Token Index: 134

Text #1

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.9089. Min Act: -0.1700

Data Index: 1366365 (Python Code)

Max Activating Token Index: 964

Text #2

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.9714. Min Act: -0.1700

Data Index: 1550747 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.9714. Min Act: -0.1700

Data Index: 595459 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8777. Min Act: -0.1700

Data Index: 1567467 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8777. Min Act: -0.1700

Data Index: 1578708 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8777. Min Act: -0.1700

Data Index: 1461774 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8777. Min Act: -0.1700

Data Index: 1637050 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8464. Min Act: -0.1700

Data Index: 1523179 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.9089. Min Act: -0.1700

Data Index: 1378305 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8464. Min Act: -0.1700

Data Index: 1426292 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8152. Min Act: -0.1700

Data Index: 1105793 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8152. Min Act: -0.1700

Data Index: 1437812 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8464. Min Act: -0.1700

Data Index: 1418784 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.7839. Min Act: -0.1700

Data Index: 1473050 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8152. Min Act: -0.1700

Data Index: 1644120 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8464. Min Act: -0.1700

Data Index: 1285791 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.7527. Min Act: -0.1700

Data Index: 156315 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8464. Min Act: -0.1700

Data Index: 221371 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 5.1902. Min Range: -5.1902

Max Act: 4.8152. Min Act: -0.1700

Data Index: 1400321 (Python Code)

Max Activating Token Index: 551