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

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

Neuron 413 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: 3.0980. Min Range: -3.0980

Max Act: 3.0980. Min Act: -0.1700

Data Index: 1547537 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1382491 (Python Code)

Max Activating Token Index: 482

Text #2

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0664. Min Act: -0.1700

Data Index: 712231 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0664. Min Act: -0.1700

Data Index: 1443256 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1259261 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0507. Min Act: -0.1700

Data Index: 1402513 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0822. Min Act: -0.1700

Data Index: 1546485 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1591229 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0033. Min Act: -0.1700

Data Index: 440744 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0191. Min Act: -0.1700

Data Index: 1166423 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0033. Min Act: -0.1700

Data Index: 1593303 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0033. Min Act: -0.1700

Data Index: 66405 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0033. Min Act: -0.1700

Data Index: 92215 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 693589 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 429530 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.0980. Min Range: -3.0980

Max Act: 3.0033. Min Act: -0.1700

Data Index: 1181920 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 87301 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 369495 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 841808 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 3.0980. Min Range: -3.0980

Max Act: 2.9875. Min Act: -0.1700

Data Index: 1066461 (C4 (Web Text))

Max Activating Token Index: 618