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

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

Neuron 538 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: 5.2322. Min Range: -5.2322

Max Act: 5.2322. Min Act: -0.1700

Data Index: 497925 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.2010. Min Act: -0.1700

Data Index: 466804 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1697. Min Act: -0.1700

Data Index: 880146 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1697. Min Act: -0.1700

Data Index: 654935 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1385. Min Act: -0.1700

Data Index: 1188992 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1385. Min Act: -0.1700

Data Index: 125705 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1697. Min Act: -0.1700

Data Index: 794290 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1072. Min Act: -0.1700

Data Index: 1308244 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0760. Min Act: -0.1700

Data Index: 78392 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0760. Min Act: -0.1700

Data Index: 98077 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0447. Min Act: -0.1700

Data Index: 888465 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0447. Min Act: -0.1700

Data Index: 703077 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0760. Min Act: -0.1700

Data Index: 964010 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0760. Min Act: -0.1700

Data Index: 1246908 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.1072. Min Act: -0.1700

Data Index: 301012 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0760. Min Act: -0.1700

Data Index: 262984 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0135. Min Act: -0.1700

Data Index: 443409 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0447. Min Act: -0.1700

Data Index: 445949 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0447. Min Act: -0.1700

Data Index: 610528 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 5.2322. Min Range: -5.2322

Max Act: 5.0447. Min Act: -0.1700

Data Index: 948791 (C4 (Web Text))

Max Activating Token Index: 742