Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 114 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.4885. Min Act: -0.1700

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.2697. Min Act: -0.1700

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.2697. Min Act: -0.1700

Data Index: 992331 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.3322. Min Act: -0.1700

Data Index: 824471 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.2072. Min Act: -0.1700

Data Index: 243630 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0822. Min Act: -0.1700

Data Index: 449091 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.2072. Min Act: -0.1700

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1447. Min Act: -0.1700

Data Index: 1299131 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1447. Min Act: -0.1700

Data Index: 581181 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1447. Min Act: -0.1700

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0822. Min Act: -0.1700

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0822. Min Act: -0.1700

Data Index: 556607 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1135. Min Act: -0.1700

Data Index: 345573 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1447. Min Act: -0.1700

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0822. Min Act: -0.1700

Data Index: 98241 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 5.4885. Min Range: -5.4885

Max Act: 4.9885. Min Act: -0.1700

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0822. Min Act: -0.1700

Data Index: 274803 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.1447. Min Act: -0.1700

Data Index: 624235 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0197. Min Act: -0.1700

Data Index: 430303 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 5.4885. Min Range: -5.4885

Max Act: 5.0197. Min Act: -0.1700

Data Index: 708657 (C4 (Web Text))

Max Activating Token Index: 393