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

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

Neuron 1091 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.1700

Data Index: 28660 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5261. Min Act: -0.1700

Data Index: 357742 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4634. Min Act: -0.1700

Data Index: 1021983 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4163. Min Act: -0.1700

Data Index: 1091959 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3536. Min Act: -0.1700

Data Index: 288622 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3536. Min Act: -0.1700

Data Index: 62544 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3693. Min Act: -0.1700

Data Index: 383057 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3536. Min Act: -0.1700

Data Index: 1044130 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3379. Min Act: -0.1700

Data Index: 788054 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3379. Min Act: -0.1700

Data Index: 328316 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3222. Min Act: -0.1700

Data Index: 844144 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1353963 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3222. Min Act: -0.1700

Data Index: 706355 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3065. Min Act: -0.1700

Data Index: 755515 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.2751. Min Act: -0.1700

Data Index: 100868 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.2908. Min Act: -0.1700

Data Index: 418816 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.2751. Min Act: -0.1700

Data Index: 637403 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.2751. Min Act: -0.1700

Data Index: 762213 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1029920 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.3065. Min Act: -0.1700

Data Index: 233471 (C4 (Web Text))

Max Activating Token Index: 5