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

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

Neuron 1945 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: 3.7846. Min Range: -3.7846

Max Act: 3.7846. Min Act: -0.1700

Data Index: 621383 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5811. Min Act: -0.1700

Data Index: 34910 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5342. Min Act: -0.1700

Data Index: 920481 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5342. Min Act: -0.1700

Data Index: 1081390 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5185. Min Act: -0.1700

Data Index: 610177 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5028. Min Act: -0.1700

Data Index: 824691 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5185. Min Act: -0.1700

Data Index: 534238 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5342. Min Act: -0.1700

Data Index: 502456 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.5028. Min Act: -0.1700

Data Index: 1314952 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4871. Min Act: -0.1700

Data Index: 958216 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4871. Min Act: -0.1700

Data Index: 305263 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4715. Min Act: -0.1700

Data Index: 483461 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4715. Min Act: -0.1700

Data Index: 1097595 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4715. Min Act: -0.1700

Data Index: 1301766 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4401. Min Act: -0.1700

Data Index: 19714 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4244. Min Act: -0.1700

Data Index: 218471 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4244. Min Act: -0.1700

Data Index: 156423 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4401. Min Act: -0.1700

Data Index: 1111979 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4558. Min Act: -0.1700

Data Index: 814108 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 3.7846. Min Range: -3.7846

Max Act: 3.4244. Min Act: -0.1700

Data Index: 1038591 (C4 (Web Text))

Max Activating Token Index: 117