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

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

Neuron 690 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: 3.6530. Min Range: -3.6530

Max Act: 3.6217. Min Act: -0.1700

Data Index: 721406 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.6530. Min Act: -0.1700

Data Index: 1260300 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5904. Min Act: -0.1700

Data Index: 862486 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.6060. Min Act: -0.1700

Data Index: 1145783 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1335784 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5747. Min Act: -0.1700

Data Index: 44583 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4494. Min Act: -0.1700

Data Index: 698584 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5434. Min Act: -0.1700

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4807. Min Act: -0.1700

Data Index: 640141 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5121. Min Act: -0.1700

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4964. Min Act: -0.1700

Data Index: 700141 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4180. Min Act: -0.1700

Data Index: 1307616 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4494. Min Act: -0.1700

Data Index: 627216 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1135034 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.3866. Min Act: -0.1700

Data Index: 605277 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4650. Min Act: -0.1700

Data Index: 1113564 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4650. Min Act: -0.1700

Data Index: 1231896 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.3866. Min Act: -0.1700

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1270846 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.6530. Min Range: -3.6530

Max Act: 3.4180. Min Act: -0.1700

Data Index: 766804 (C4 (Web Text))

Max Activating Token Index: 816