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

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

Neuron 1845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1635. Min Act: -0.1700

Data Index: 264069 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 864264 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1635. Min Act: -0.1700

Data Index: 853262 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1010. Min Act: -0.1700

Data Index: 1275295 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 169064 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1947. Min Act: -0.1700

Data Index: 312190 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1010. Min Act: -0.1700

Data Index: 779121 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 1069970 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0385. Min Act: -0.1700

Data Index: 582084 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 628241 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 580951 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 1347523 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 244187 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.1322. Min Act: -0.1700

Data Index: 687886 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0072. Min Act: -0.1700

Data Index: 729254 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0385. Min Act: -0.1700

Data Index: 296385 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0385. Min Act: -0.1700

Data Index: 1146500 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 1238217 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 5.1947. Min Range: -5.1947

Max Act: 4.9760. Min Act: -0.1700

Data Index: 782199 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 5.1947. Min Range: -5.1947

Max Act: 5.0697. Min Act: -0.1700

Data Index: 626987 (C4 (Web Text))

Max Activating Token Index: 566