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

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

Neuron 1107 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: 5.3060. Min Range: -5.3060

Max Act: 5.2747. Min Act: -0.1700

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.2747. Min Act: -0.1700

Data Index: 284246 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.3060. Min Act: -0.1700

Data Index: 314420 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.2122. Min Act: -0.1700

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.2435. Min Act: -0.1700

Data Index: 260050 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1497. Min Act: -0.1700

Data Index: 1046931 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1810. Min Act: -0.1700

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1810. Min Act: -0.1700

Data Index: 466062 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1497. Min Act: -0.1700

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1497. Min Act: -0.1700

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0872. Min Act: -0.1700

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1185. Min Act: -0.1700

Data Index: 1132425 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0872. Min Act: -0.1700

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0872. Min Act: -0.1700

Data Index: 72649 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.1497. Min Act: -0.1700

Data Index: 429778 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0872. Min Act: -0.1700

Data Index: 528171 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0247. Min Act: -0.1699

Data Index: 817074 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0560. Min Act: -0.1700

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 5.3060. Min Range: -5.3060

Max Act: 5.0247. Min Act: -0.1700

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 5.3060. Min Range: -5.3060

Max Act: 4.9935. Min Act: -0.1700

Data Index: 981203 (C4 (Web Text))

Max Activating Token Index: 176