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

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

Neuron 397 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: 3.8705. Min Range: -3.8705

Max Act: 3.8392. Min Act: -0.1700

Data Index: 181278 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8705. Min Act: -0.1700

Data Index: 150848 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1357047 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8392. Min Act: -0.1700

Data Index: 982698 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8392. Min Act: -0.1700

Data Index: 966770 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8392. Min Act: -0.1700

Data Index: 414326 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1262834 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.8079. Min Act: -0.1700

Data Index: 640850 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1188135 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7923. Min Act: -0.1700

Data Index: 761449 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1315389 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7610. Min Act: -0.1700

Data Index: 782532 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7766. Min Act: -0.1700

Data Index: 250462 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7297. Min Act: -0.1700

Data Index: 1136030 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7610. Min Act: -0.1700

Data Index: 1278260 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7297. Min Act: -0.1700

Data Index: 984194 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7297. Min Act: -0.1700

Data Index: 791589 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7454. Min Act: -0.1700

Data Index: 1353998 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7610. Min Act: -0.1700

Data Index: 896335 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 3.8705. Min Range: -3.8705

Max Act: 3.7297. Min Act: -0.1700

Data Index: 359811 (C4 (Web Text))

Max Activating Token Index: 478