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

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

Neuron 1754 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: 3.7968. Min Range: -3.7968

Max Act: 3.7655. Min Act: -0.1700

Data Index: 526231 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7968. Min Act: -0.1700

Data Index: 484058 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7968. Min Act: -0.1700

Data Index: 125919 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1068030 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7342. Min Act: -0.1700

Data Index: 1049565 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6716. Min Act: -0.1700

Data Index: 13556 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7342. Min Act: -0.1700

Data Index: 1136965 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7029. Min Act: -0.1700

Data Index: 785173 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1280070 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7029. Min Act: -0.1700

Data Index: 476616 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1153099 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.7029. Min Act: -0.1700

Data Index: 338764 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6716. Min Act: -0.1700

Data Index: 670826 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6403. Min Act: -0.1700

Data Index: 210578 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6090. Min Act: -0.1700

Data Index: 421681 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6090. Min Act: -0.1700

Data Index: 214408 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5464. Min Act: -0.1700

Data Index: 464870 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6090. Min Act: -0.1700

Data Index: 1145589 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.6090. Min Act: -0.1700

Data Index: 604789 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 3.7968. Min Range: -3.7968

Max Act: 3.5777. Min Act: -0.1700

Data Index: 1038646 (C4 (Web Text))

Max Activating Token Index: 312