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

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

Neuron 705 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: 3.4557. Min Range: -3.4557

Max Act: 3.4557. Min Act: -0.1700

Data Index: 1029673 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.3773. Min Act: -0.1700

Data Index: 1254557 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.3616. Min Act: -0.1700

Data Index: 600986 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.3616. Min Act: -0.1700

Data Index: 116148 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.2674. Min Act: -0.1700

Data Index: 278180 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.2202. Min Act: -0.1700

Data Index: 1265519 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.2202. Min Act: -0.1700

Data Index: 170884 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1212453 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1888. Min Act: -0.1700

Data Index: 1642780 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1888. Min Act: -0.1700

Data Index: 823052 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1730. Min Act: -0.1700

Data Index: 810785 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1415. Min Act: -0.1700

Data Index: 284699 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1573. Min Act: -0.1700

Data Index: 752960 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1888. Min Act: -0.1700

Data Index: 378430 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1573. Min Act: -0.1700

Data Index: 1220018 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1415. Min Act: -0.1700

Data Index: 1359232 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1415. Min Act: -0.1700

Data Index: 104030 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1100. Min Act: -0.1700

Data Index: 241809 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1163591 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 3.4557. Min Range: -3.4557

Max Act: 3.1573. Min Act: -0.1700

Data Index: 104225 (C4 (Web Text))

Max Activating Token Index: 473