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

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

Neuron 1331 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.1284. Min Act: -0.1700

Data Index: 24575 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.1127. Min Act: -0.1700

Data Index: 962260 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.1127. Min Act: -0.1700

Data Index: 731072 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.1127. Min Act: -0.1700

Data Index: 887576 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0969. Min Act: -0.1700

Data Index: 1328309 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0969. Min Act: -0.1700

Data Index: 106651 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0653. Min Act: -0.1700

Data Index: 631316 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0969. Min Act: -0.1700

Data Index: 896328 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0811. Min Act: -0.1700

Data Index: 1320704 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0811. Min Act: -0.1700

Data Index: 1105271 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0811. Min Act: -0.1700

Data Index: 782652 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0811. Min Act: -0.1700

Data Index: 223621 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0653. Min Act: -0.1700

Data Index: 1069608 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0496. Min Act: -0.1700

Data Index: 346501 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0496. Min Act: -0.1700

Data Index: 499692 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0653. Min Act: -0.1700

Data Index: 684914 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0653. Min Act: -0.1700

Data Index: 869418 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0653. Min Act: -0.1700

Data Index: 243046 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1188270 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.1284. Min Range: -3.1284

Max Act: 3.0496. Min Act: -0.1700

Data Index: 424294 (C4 (Web Text))

Max Activating Token Index: 1007