Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 944 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.9590. Min Act: -0.1700

Data Index: 472464 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.9278. Min Act: -0.1700

Data Index: 753365 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8652. Min Act: -0.1700

Data Index: 1343587 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8965. Min Act: -0.1700

Data Index: 284630 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8652. Min Act: -0.1700

Data Index: 282778 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8027. Min Act: -0.1700

Data Index: 627942 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.8339. Min Act: -0.1700

Data Index: 405198 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7401. Min Act: -0.1700

Data Index: 1126103 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7714. Min Act: -0.1700

Data Index: 438457 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7401. Min Act: -0.1700

Data Index: 15365 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7401. Min Act: -0.1700

Data Index: 175018 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7088. Min Act: -0.1700

Data Index: 569098 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7088. Min Act: -0.1700

Data Index: 1172027 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7401. Min Act: -0.1700

Data Index: 1180458 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.7401. Min Act: -0.1700

Data Index: 257345 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.6775. Min Act: -0.1700

Data Index: 205184 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.6462. Min Act: -0.1700

Data Index: 169051 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.6149. Min Act: -0.1700

Data Index: 749346 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.6149. Min Act: -0.1700

Data Index: 511731 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.9590. Min Range: -3.9590

Max Act: 3.6462. Min Act: -0.1700

Data Index: 996701 (C4 (Web Text))

Max Activating Token Index: 244