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

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

Neuron 589 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0475. Min Range: -5.0475

Max Act: 5.0475. Min Act: -0.1700

Data Index: 1357009 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.9225. Min Act: -0.1700

Data Index: 598757 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.8600. Min Act: -0.1700

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.8288. Min Act: -0.1700

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7663. Min Act: -0.1700

Data Index: 957960 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.8600. Min Act: -0.1700

Data Index: 1078829 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7975. Min Act: -0.1700

Data Index: 397184 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7663. Min Act: -0.1700

Data Index: 568527 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7975. Min Act: -0.1700

Data Index: 1028748 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7037. Min Act: -0.1700

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7037. Min Act: -0.1699

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.7037. Min Act: -0.1700

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.6412. Min Act: -0.1700

Data Index: 429643 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.6725. Min Act: -0.1700

Data Index: 1072625 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.6412. Min Act: -0.1700

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.6100. Min Act: -0.1700

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.5475. Min Act: -0.1700

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.5787. Min Act: -0.1700

Data Index: 1310128 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.5787. Min Act: -0.1700

Data Index: 600484 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 5.0475. Min Range: -5.0475

Max Act: 4.6100. Min Act: -0.1700

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 948