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

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

Neuron 153 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: 3.8280. Min Range: -3.8280

Max Act: 3.8280. Min Act: -0.1700

Data Index: 723011 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.7967. Min Act: -0.1700

Data Index: 71566 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.7341. Min Act: -0.1700

Data Index: 206235 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.7341. Min Act: -0.1700

Data Index: 673291 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.7341. Min Act: -0.1700

Data Index: 30785 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.6715. Min Act: -0.1700

Data Index: 254771 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1293489 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.6402. Min Act: -0.1700

Data Index: 99513 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.6402. Min Act: -0.1700

Data Index: 1296860 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 999160 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 1196404 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 976021 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 609068 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 160311 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 711484 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 19850 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 401569 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5776. Min Act: -0.1700

Data Index: 1002015 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5463. Min Act: -0.1700

Data Index: 1207723 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 3.8280. Min Range: -3.8280

Max Act: 3.5463. Min Act: -0.1700

Data Index: 504441 (C4 (Web Text))

Max Activating Token Index: 11