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

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

Neuron 171 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: 4.1106. Min Range: -4.1106

Max Act: 4.1106. Min Act: -0.1700

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9855. Min Act: -0.1700

Data Index: 577875 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 4.1106. Min Range: -4.1106

Max Act: 4.0168. Min Act: -0.1700

Data Index: 257753 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 1330578 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9855. Min Act: -0.1700

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9855. Min Act: -0.1700

Data Index: 242075 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 1323848 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 136672 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 1079659 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 1193520 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 952127 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 1011190 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8917. Min Act: -0.1700

Data Index: 650755 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9543. Min Act: -0.1700

Data Index: 869985 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 1351949 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 26684 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9230. Min Act: -0.1700

Data Index: 197999 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8604. Min Act: -0.1700

Data Index: 404333 (C4 (Web Text))

Max Activating Token Index: 91