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

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

Neuron 490 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: 3.3677. Min Range: -3.3677

Max Act: 3.3677. Min Act: -0.1700

Data Index: 1280044 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.2892. Min Act: -0.1700

Data Index: 1233291 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.2735. Min Act: -0.1700

Data Index: 159846 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.2578. Min Act: -0.1700

Data Index: 620378 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1792. Min Act: -0.1700

Data Index: 1236876 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1949. Min Act: -0.1700

Data Index: 597242 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1792. Min Act: -0.1700

Data Index: 1192331 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1792. Min Act: -0.1700

Data Index: 488009 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1634. Min Act: -0.1700

Data Index: 253088 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1634. Min Act: -0.1700

Data Index: 173638 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1477. Min Act: -0.1700

Data Index: 975338 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1477. Min Act: -0.1700

Data Index: 624262 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 303346 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1319. Min Act: -0.1700

Data Index: 852520 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 788614 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1004. Min Act: -0.1700

Data Index: 1042141 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 524198 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 1199017 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 973339 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 3.3677. Min Range: -3.3677

Max Act: 3.1162. Min Act: -0.1700

Data Index: 472345 (C4 (Web Text))

Max Activating Token Index: 559