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

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

Neuron 1533 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: 3.4396. Min Range: -3.4396

Max Act: 3.4396. Min Act: -0.1700

Data Index: 163893 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1883. Min Act: -0.1700

Data Index: 815437 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.2041. Min Act: -0.1700

Data Index: 397380 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1180002 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1726. Min Act: -0.1700

Data Index: 951939 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1726. Min Act: -0.1700

Data Index: 661273 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1726. Min Act: -0.1700

Data Index: 765746 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1568. Min Act: -0.1700

Data Index: 916220 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1096. Min Act: -0.1700

Data Index: 1310938 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1411. Min Act: -0.1700

Data Index: 163597 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0938. Min Act: -0.1700

Data Index: 981764 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1096. Min Act: -0.1700

Data Index: 253094 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1253. Min Act: -0.1700

Data Index: 538444 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0780. Min Act: -0.1700

Data Index: 34585 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0938. Min Act: -0.1700

Data Index: 210134 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.1096. Min Act: -0.1700

Data Index: 575747 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0780. Min Act: -0.1700

Data Index: 860182 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0938. Min Act: -0.1700

Data Index: 864139 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0780. Min Act: -0.1700

Data Index: 24738 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 3.4396. Min Range: -3.4396

Max Act: 3.0780. Min Act: -0.1700

Data Index: 215094 (C4 (Web Text))

Max Activating Token Index: 229