Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 271 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.5077. Min Act: -0.1700

Data Index: 717951 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.5702. Min Act: -0.1700

Data Index: 225892 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.4140. Min Act: -0.1700

Data Index: 17365 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.4140. Min Act: -0.1700

Data Index: 117166 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.3515. Min Act: -0.1700

Data Index: 181904 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.3515. Min Act: -0.1700

Data Index: 507138 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.3515. Min Act: -0.1700

Data Index: 809977 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.3202. Min Act: -0.1700

Data Index: 513337 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.3515. Min Act: -0.1700

Data Index: 1060673 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.2577. Min Act: -0.1700

Data Index: 1210032 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.2265. Min Act: -0.1700

Data Index: 569065 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.1952. Min Act: -0.1700

Data Index: 1141953 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.2577. Min Act: -0.1700

Data Index: 803478 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.1640. Min Act: -0.1700

Data Index: 801815 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.1640. Min Act: -0.1700

Data Index: 916264 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.0702. Min Act: -0.1700

Data Index: 900903 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.0077. Min Act: -0.1700

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 5.5702. Min Range: -5.5702

Max Act: 4.9452. Min Act: -0.1700

Data Index: 1198985 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 5.5702. Min Range: -5.5702

Max Act: 4.9452. Min Act: -0.1700

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 5.5702. Min Range: -5.5702

Max Act: 5.0077. Min Act: -0.1700

Data Index: 340542 (C4 (Web Text))

Max Activating Token Index: 801