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

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

Neuron 870 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: 3.7758. Min Range: -3.7758

Max Act: 3.7758. Min Act: -0.1700

Data Index: 1171537 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.7445. Min Act: -0.1700

Data Index: 226430 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6506. Min Act: -0.1700

Data Index: 1069379 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6506. Min Act: -0.1700

Data Index: 1074568 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6506. Min Act: -0.1700

Data Index: 492480 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6193. Min Act: -0.1700

Data Index: 646224 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6193. Min Act: -0.1700

Data Index: 765082 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.6037. Min Act: -0.1700

Data Index: 452760 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5880. Min Act: -0.1700

Data Index: 1148659 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5723. Min Act: -0.1700

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5567. Min Act: -0.1700

Data Index: 358868 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5410. Min Act: -0.1700

Data Index: 936111 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5410. Min Act: -0.1700

Data Index: 1142673 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5410. Min Act: -0.1700

Data Index: 355297 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5254. Min Act: -0.1700

Data Index: 188249 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5097. Min Act: -0.1700

Data Index: 1310838 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5410. Min Act: -0.1700

Data Index: 843983 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.4940. Min Act: -0.1700

Data Index: 934843 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.5097. Min Act: -0.1700

Data Index: 1092871 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 3.7758. Min Range: -3.7758

Max Act: 3.4940. Min Act: -0.1700

Data Index: 216777 (C4 (Web Text))

Max Activating Token Index: 916