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

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

Neuron 630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.9544. Min Act: -0.1699

Data Index: 955824 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.9700. Min Act: -0.1700

Data Index: 10740 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8918. Min Act: -0.1700

Data Index: 447508 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8606. Min Act: -0.1700

Data Index: 234467 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8293. Min Act: -0.1700

Data Index: 960172 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7667. Min Act: -0.1700

Data Index: 427669 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8136. Min Act: -0.1700

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7824. Min Act: -0.1700

Data Index: 295164 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8136. Min Act: -0.1700

Data Index: 1039623 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7824. Min Act: -0.1700

Data Index: 490729 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7980. Min Act: -0.1700

Data Index: 595598 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7980. Min Act: -0.1700

Data Index: 779362 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7980. Min Act: -0.1700

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.8136. Min Act: -0.1699

Data Index: 1299301 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7824. Min Act: -0.1700

Data Index: 739195 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7824. Min Act: -0.1700

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1275234 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7824. Min Act: -0.1700

Data Index: 938076 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1220699 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.9700. Min Range: -3.9700

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1139222 (C4 (Web Text))

Max Activating Token Index: 432