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

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

Neuron 897 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.0695. Min Act: -0.1700

Data Index: 709596 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.1945. Min Act: -0.1700

Data Index: 1322942 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.1008. Min Act: -0.1700

Data Index: 167879 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.0070. Min Act: -0.1700

Data Index: 1057324 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.0383. Min Act: -0.1700

Data Index: 79423 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9758. Min Act: -0.1700

Data Index: 1128569 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9758. Min Act: -0.1700

Data Index: 1195844 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 5.1945. Min Range: -5.1945

Max Act: 5.0383. Min Act: -0.1700

Data Index: 1030669 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9758. Min Act: -0.1700

Data Index: 727025 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9445. Min Act: -0.1700

Data Index: 1150414 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 806757 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9445. Min Act: -0.1700

Data Index: 890586 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 595294 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 928157 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.8820. Min Act: -0.1700

Data Index: 392372 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 509667 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 1094356 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.7570. Min Act: -0.1700

Data Index: 96718 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.9133. Min Act: -0.1700

Data Index: 1049133 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 5.1945. Min Range: -5.1945

Max Act: 4.8508. Min Act: -0.1700

Data Index: 25797 (C4 (Web Text))

Max Activating Token Index: 244