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

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

Neuron 1881 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: 7.1215. Min Range: -7.1215

Max Act: 7.1215. Min Act: -0.1700

Data Index: 1067067 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 7.1215. Min Range: -7.1215

Max Act: 7.0277. Min Act: -0.1700

Data Index: 545201 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 7.1215. Min Range: -7.1215

Max Act: 7.0902. Min Act: -0.1700

Data Index: 783153 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.9965. Min Act: -0.1700

Data Index: 1331257 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.8090. Min Act: -0.1700

Data Index: 408989 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.8402. Min Act: -0.1700

Data Index: 278820 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.7777. Min Act: -0.1700

Data Index: 725215 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.7777. Min Act: -0.1700

Data Index: 524893 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6840. Min Act: -0.1700

Data Index: 938527 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6840. Min Act: -0.1700

Data Index: 945776 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6527. Min Act: -0.1700

Data Index: 283756 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6840. Min Act: -0.1700

Data Index: 778084 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6215. Min Act: -0.1700

Data Index: 1334029 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.5902. Min Act: -0.1700

Data Index: 552260 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.5277. Min Act: -0.1700

Data Index: 762388 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.6215. Min Act: -0.1700

Data Index: 75296 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.5902. Min Act: -0.1700

Data Index: 1120606 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.4965. Min Act: -0.1700

Data Index: 771131 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.5277. Min Act: -0.1700

Data Index: 363871 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 7.1215. Min Range: -7.1215

Max Act: 6.5277. Min Act: -0.1700

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 779