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

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

Neuron 1952 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.9350. Min Act: -0.1700

Data Index: 1355646 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.7787. Min Act: -0.1700

Data Index: 315087 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.7474. Min Act: -0.1700

Data Index: 61004 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5909. Min Act: -0.1700

Data Index: 419977 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.6222. Min Act: -0.1700

Data Index: 296695 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.6222. Min Act: -0.1700

Data Index: 857656 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5752. Min Act: -0.1700

Data Index: 862380 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1010580 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5909. Min Act: -0.1700

Data Index: 733713 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5282. Min Act: -0.1700

Data Index: 789953 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5439. Min Act: -0.1700

Data Index: 756641 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5439. Min Act: -0.1700

Data Index: 235746 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5126. Min Act: -0.1700

Data Index: 661158 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5595. Min Act: -0.1700

Data Index: 1293164 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.5439. Min Act: -0.1700

Data Index: 1026432 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.4812. Min Act: -0.1700

Data Index: 419534 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.4655. Min Act: -0.1700

Data Index: 1123895 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.4812. Min Act: -0.1700

Data Index: 1332458 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.4812. Min Act: -0.1700

Data Index: 568377 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.9350. Min Range: -3.9350

Max Act: 3.4655. Min Act: -0.1700

Data Index: 539165 (C4 (Web Text))

Max Activating Token Index: 1005