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

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

Neuron 740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.1312. Min Act: -0.1700

Data Index: 187490 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.1937. Min Act: -0.1700

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0999. Min Act: -0.1700

Data Index: 843089 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0687. Min Act: -0.1700

Data Index: 1070676 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0687. Min Act: -0.1700

Data Index: 935959 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0687. Min Act: -0.1700

Data Index: 488745 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0374. Min Act: -0.1700

Data Index: 416732 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9749. Min Act: -0.1700

Data Index: 628130 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0062. Min Act: -0.1700

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9124. Min Act: -0.1700

Data Index: 22099 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 5.1937. Min Range: -5.1937

Max Act: 5.0374. Min Act: -0.1700

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9124. Min Act: -0.1700

Data Index: 706523 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9749. Min Act: -0.1700

Data Index: 405735 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9437. Min Act: -0.1700

Data Index: 1059926 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9749. Min Act: -0.1700

Data Index: 153057 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.8812. Min Act: -0.1700

Data Index: 1161653 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9124. Min Act: -0.1700

Data Index: 197249 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9124. Min Act: -0.1700

Data Index: 32403 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9124. Min Act: -0.1700

Data Index: 771571 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 5.1937. Min Range: -5.1937

Max Act: 4.9437. Min Act: -0.1700

Data Index: 1066865 (C4 (Web Text))

Max Activating Token Index: 469