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

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

Neuron 1518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1322381 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.7161. Min Act: -0.1700

Data Index: 241211 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6535. Min Act: -0.1700

Data Index: 939045 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6379. Min Act: -0.1700

Data Index: 165732 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6535. Min Act: -0.1700

Data Index: 202381 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6066. Min Act: -0.1700

Data Index: 385724 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6222. Min Act: -0.1700

Data Index: 209857 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6066. Min Act: -0.1700

Data Index: 218755 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.6066. Min Act: -0.1700

Data Index: 614172 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1146774 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5752. Min Act: -0.1700

Data Index: 749865 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5596. Min Act: -0.1700

Data Index: 508624 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1145950 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5596. Min Act: -0.1700

Data Index: 563416 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5596. Min Act: -0.1700

Data Index: 834223 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5439. Min Act: -0.1700

Data Index: 275386 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5283. Min Act: -0.1700

Data Index: 814014 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5439. Min Act: -0.1700

Data Index: 296873 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5283. Min Act: -0.1700

Data Index: 301991 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 3.7161. Min Range: -3.7161

Max Act: 3.5283. Min Act: -0.1700

Data Index: 306278 (C4 (Web Text))

Max Activating Token Index: 204