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

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

Neuron 2041 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5973. Min Act: -0.1700

Data Index: 1233994 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6912. Min Act: -0.1700

Data Index: 984706 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5660. Min Act: -0.1700

Data Index: 421915 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5973. Min Act: -0.1700

Data Index: 632726 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5973. Min Act: -0.1700

Data Index: 600636 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6912. Min Act: -0.1700

Data Index: 716423 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1150460 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5346. Min Act: -0.1700

Data Index: 539726 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.6599. Min Act: -0.1700

Data Index: 1272626 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5033. Min Act: -0.1700

Data Index: 1087172 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5346. Min Act: -0.1700

Data Index: 757750 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5033. Min Act: -0.1700

Data Index: 985158 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5346. Min Act: -0.1700

Data Index: 881119 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5033. Min Act: -0.1700

Data Index: 664571 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5033. Min Act: -0.1700

Data Index: 163551 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5660. Min Act: -0.1700

Data Index: 337185 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.4406. Min Act: -0.1700

Data Index: 879033 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.4092. Min Act: -0.1700

Data Index: 148696 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.5346. Min Act: -0.1700

Data Index: 652357 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 3.6912. Min Range: -3.6912

Max Act: 3.3779. Min Act: -0.1700

Data Index: 169852 (C4 (Web Text))

Max Activating Token Index: 363