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

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

Neuron 1091 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: 5.7045. Min Range: -5.7045

Max Act: 5.7045. Min Act: -0.1700

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.3920. Min Act: -0.1700

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.4232. Min Act: -0.1700

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.3920. Min Act: -0.1700

Data Index: 127926 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.2982. Min Act: -0.1700

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.3295. Min Act: -0.1700

Data Index: 492578 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.2982. Min Act: -0.1700

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1732. Min Act: -0.1700

Data Index: 1143994 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.2045. Min Act: -0.1700

Data Index: 1330911 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1420. Min Act: -0.1700

Data Index: 1464666 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1107. Min Act: -0.1700

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1107. Min Act: -0.1700

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1420. Min Act: -0.1700

Data Index: 72649 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0795. Min Act: -0.1700

Data Index: 1095623 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0795. Min Act: -0.1700

Data Index: 719688 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.1107. Min Act: -0.1700

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0795. Min Act: -0.1700

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0170. Min Act: -0.1700

Data Index: 1192776 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0170. Min Act: -0.1700

Data Index: 1305960 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 5.7045. Min Range: -5.7045

Max Act: 5.0170. Min Act: -0.1700

Data Index: 1044665 (C4 (Web Text))

Max Activating Token Index: 193