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

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

Neuron 929 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: 3.6523. Min Range: -3.6523

Max Act: 3.6523. Min Act: -0.1700

Data Index: 177489 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.6054. Min Act: -0.1700

Data Index: 1239996 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.6054. Min Act: -0.1700

Data Index: 1507034 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.6054. Min Act: -0.1700

Data Index: 968694 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.5741. Min Act: -0.1700

Data Index: 1109733 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.5741. Min Act: -0.1700

Data Index: 734414 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4957. Min Act: -0.1700

Data Index: 581277 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4957. Min Act: -0.1700

Data Index: 1605684 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4644. Min Act: -0.1700

Data Index: 4611 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4801. Min Act: -0.1700

Data Index: 188233 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4487. Min Act: -0.1700

Data Index: 842244 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4487. Min Act: -0.1700

Data Index: 1183738 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4174. Min Act: -0.1700

Data Index: 1156599 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4331. Min Act: -0.1700

Data Index: 233658 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4331. Min Act: -0.1700

Data Index: 274945 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4331. Min Act: -0.1700

Data Index: 1475014 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4174. Min Act: -0.1700

Data Index: 674481 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.4017. Min Act: -0.1700

Data Index: 477880 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1567519 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 3.6523. Min Range: -3.6523

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1459537 (Python Code)

Max Activating Token Index: 780