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

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

Neuron 767 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: 5.4317. Min Range: -5.4317

Max Act: 5.3692. Min Act: -0.1700

Data Index: 291351 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.4317. Min Act: -0.1700

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3692. Min Act: -0.1700

Data Index: 1025112 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3067. Min Act: -0.1700

Data Index: 1070952 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3692. Min Act: -0.1700

Data Index: 896167 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3379. Min Act: -0.1700

Data Index: 756034 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3379. Min Act: -0.1700

Data Index: 1341870 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2754. Min Act: -0.1700

Data Index: 629047 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3379. Min Act: -0.1700

Data Index: 514638 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3067. Min Act: -0.1700

Data Index: 1048661 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3067. Min Act: -0.1700

Data Index: 1205644 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 838491 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2754. Min Act: -0.1699

Data Index: 199091 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 752005 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2754. Min Act: -0.1700

Data Index: 311213 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2129. Min Act: -0.1700

Data Index: 149661 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 1132832 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2129. Min Act: -0.1700

Data Index: 1208011 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2129. Min Act: -0.1700

Data Index: 930976 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 681862 (C4 (Web Text))

Max Activating Token Index: 762