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

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

Neuron 230 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: 3.7702. Min Range: -3.7702

Max Act: 3.7702. Min Act: -0.1700

Data Index: 113773 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.7233. Min Act: -0.1700

Data Index: 1237648 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.7076. Min Act: -0.1700

Data Index: 331147 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.7076. Min Act: -0.1700

Data Index: 185132 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6763. Min Act: -0.1700

Data Index: 1093022 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6294. Min Act: -0.1700

Data Index: 441501 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6763. Min Act: -0.1700

Data Index: 24820 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6607. Min Act: -0.1700

Data Index: 1251718 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6607. Min Act: -0.1700

Data Index: 17390 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6450. Min Act: -0.1700

Data Index: 737511 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6450. Min Act: -0.1700

Data Index: 304699 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6450. Min Act: -0.1700

Data Index: 933767 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6294. Min Act: -0.1700

Data Index: 1213189 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6607. Min Act: -0.1700

Data Index: 783665 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6450. Min Act: -0.1700

Data Index: 603216 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6294. Min Act: -0.1700

Data Index: 995917 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.5980. Min Act: -0.1700

Data Index: 1145543 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6137. Min Act: -0.1700

Data Index: 930722 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.6137. Min Act: -0.1700

Data Index: 163689 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.7702. Min Range: -3.7702

Max Act: 3.5980. Min Act: -0.1700

Data Index: 310321 (C4 (Web Text))

Max Activating Token Index: 168