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

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

Neuron 663 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: 3.7965. Min Range: -3.7965

Max Act: 3.7965. Min Act: -0.1700

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7809. Min Act: -0.1700

Data Index: 807330 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 830467 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 1288313 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 52430 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 1288795 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 140800 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7340. Min Act: -0.1700

Data Index: 220690 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7340. Min Act: -0.1700

Data Index: 621015 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7340. Min Act: -0.1700

Data Index: 30076 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7496. Min Act: -0.1700

Data Index: 328388 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7340. Min Act: -0.1700

Data Index: 409700 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7183. Min Act: -0.1700

Data Index: 821218 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7027. Min Act: -0.1700

Data Index: 63158 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7183. Min Act: -0.1700

Data Index: 215872 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7183. Min Act: -0.1700

Data Index: 177705 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7183. Min Act: -0.1700

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7027. Min Act: -0.1700

Data Index: 970674 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7340. Min Act: -0.1700

Data Index: 493974 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.7965. Min Range: -3.7965

Max Act: 3.7027. Min Act: -0.1700

Data Index: 1068356 (C4 (Web Text))

Max Activating Token Index: 24