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

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

Neuron 453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.8336. Min Act: -0.1700

Data Index: 22300 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 731013 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 1641907 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 41008 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 588381 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 526411 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 352411 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 810007 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 816241 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 14484 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7397. Min Act: -0.1700

Data Index: 864166 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6771. Min Act: -0.1700

Data Index: 454113 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 916080 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1077757 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6771. Min Act: -0.1700

Data Index: 312194 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1311346 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6771. Min Act: -0.1700

Data Index: 841616 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6458. Min Act: -0.1700

Data Index: 639697 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6771. Min Act: -0.1700

Data Index: 507200 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 3.8336. Min Range: -3.8336

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1232414 (C4 (Web Text))

Max Activating Token Index: 145