Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1014 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0001. Min Range: -3.0001

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1171880 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.9583. Min Act: -0.1700

Data Index: 719047 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.9605. Min Act: -0.1700

Data Index: 1076057 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.9538. Min Act: -0.1700

Data Index: 142639 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.9008. Min Act: -0.1700

Data Index: 259516 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8929. Min Act: -0.1700

Data Index: 984211 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.9100. Min Act: -0.1700

Data Index: 737971 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8792. Min Act: -0.1700

Data Index: 620928 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8942. Min Act: -0.1700

Data Index: 738615 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8829. Min Act: -0.1700

Data Index: 1135399 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8797. Min Act: -0.1700

Data Index: 353908 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8481. Min Act: -0.1700

Data Index: 1283915 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8403. Min Act: -0.1700

Data Index: 476720 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8168. Min Act: -0.1700

Data Index: 890375 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.7787. Min Act: -0.1700

Data Index: 1196566 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8014. Min Act: -0.1700

Data Index: 1029346 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.8031. Min Act: -0.1700

Data Index: 133123 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.7601. Min Act: -0.1700

Data Index: 153694 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.7496. Min Act: -0.1700

Data Index: 855133 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 3.0001. Min Range: -3.0001

Max Act: 2.7554. Min Act: -0.1700

Data Index: 636299 (C4 (Web Text))

Max Activating Token Index: 115