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

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

Neuron 858 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1677. Min Act: -0.1700

Data Index: 1350770 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1520. Min Act: -0.1700

Data Index: 351141 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.1362. Min Act: -0.1700

Data Index: 1214940 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0889. Min Act: -0.1700

Data Index: 894684 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0889. Min Act: -0.1700

Data Index: 971301 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0889. Min Act: -0.1700

Data Index: 195027 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0731. Min Act: -0.1700

Data Index: 825650 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0416. Min Act: -0.1700

Data Index: 9645 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0574. Min Act: -0.1700

Data Index: 510111 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0574. Min Act: -0.1700

Data Index: 1187759 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0731. Min Act: -0.1700

Data Index: 207134 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0416. Min Act: -0.1700

Data Index: 5705 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0731. Min Act: -0.1700

Data Index: 853345 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0574. Min Act: -0.1700

Data Index: 562015 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0258. Min Act: -0.1700

Data Index: 294579 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0258. Min Act: -0.1700

Data Index: 920161 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0416. Min Act: -0.1700

Data Index: 1135291 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0416. Min Act: -0.1700

Data Index: 488581 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0574. Min Act: -0.1700

Data Index: 331967 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.1677. Min Range: -3.1677

Max Act: 3.0258. Min Act: -0.1700

Data Index: 214021 (C4 (Web Text))

Max Activating Token Index: 851