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

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

Neuron 1182 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.9945. Min Act: -0.1700

Data Index: 790574 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.7757. Min Act: -0.1700

Data Index: 681591 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.7757. Min Act: -0.1700

Data Index: 117140 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.8070. Min Act: -0.1700

Data Index: 616979 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.6820. Min Act: -0.1700

Data Index: 921726 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.7132. Min Act: -0.1700

Data Index: 285459 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.7132. Min Act: -0.1700

Data Index: 263589 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.6820. Min Act: -0.1700

Data Index: 1183262 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.6507. Min Act: -0.1700

Data Index: 338147 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5882. Min Act: -0.1700

Data Index: 673120 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.6195. Min Act: -0.1700

Data Index: 587142 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.6195. Min Act: -0.1700

Data Index: 644998 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5882. Min Act: -0.1700

Data Index: 586821 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5257. Min Act: -0.1700

Data Index: 1207931 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5570. Min Act: -0.1700

Data Index: 796490 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5882. Min Act: -0.1700

Data Index: 32362 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5570. Min Act: -0.1700

Data Index: 189122 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5882. Min Act: -0.1700

Data Index: 997892 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5257. Min Act: -0.1700

Data Index: 204139 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 5.9945. Min Range: -5.9945

Max Act: 5.5257. Min Act: -0.1700

Data Index: 956350 (C4 (Web Text))

Max Activating Token Index: 488