Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1983 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1321131 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7988. Min Act: -0.1700

Data Index: 73308 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.8144. Min Act: -0.1700

Data Index: 614923 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.8144. Min Act: -0.1700

Data Index: 13708 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1016565 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7206. Min Act: -0.1700

Data Index: 231023 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7206. Min Act: -0.1700

Data Index: 1094050 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7206. Min Act: -0.1700

Data Index: 1626852 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7362. Min Act: -0.1700

Data Index: 294456 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1034566 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.7206. Min Act: -0.1700

Data Index: 1595265 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1507577 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6893. Min Act: -0.1700

Data Index: 152169 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6267. Min Act: -0.1700

Data Index: 1631081 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6736. Min Act: -0.1700

Data Index: 229584 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6893. Min Act: -0.1700

Data Index: 265091 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6580. Min Act: -0.1700

Data Index: 869393 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6893. Min Act: -0.1700

Data Index: 800507 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6736. Min Act: -0.1700

Data Index: 697081 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.8457. Min Range: -3.8457

Max Act: 3.6736. Min Act: -0.1700

Data Index: 119848 (C4 (Web Text))

Max Activating Token Index: 164