Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1324 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5583. Min Act: -0.1700

Data Index: 250023 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5422. Min Act: -0.1700

Data Index: 315623 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.5260. Min Act: -0.1700

Data Index: 1165930 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4612. Min Act: -0.1700

Data Index: 676109 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4287. Min Act: -0.1700

Data Index: 1015400 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4449. Min Act: -0.1700

Data Index: 879793 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4449. Min Act: -0.1700

Data Index: 195810 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4287. Min Act: -0.1700

Data Index: 1551671 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.4124. Min Act: -0.1700

Data Index: 943002 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 1241157 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 866341 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3797. Min Act: -0.1700

Data Index: 473445 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 34478 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3797. Min Act: -0.1700

Data Index: 443987 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 305241 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 65651 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 489718 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 482212 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3797. Min Act: -0.1700

Data Index: 583095 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 2.5583. Min Range: -2.5583

Max Act: 2.3961. Min Act: -0.1700

Data Index: 1472938 (Python Code)

Max Activating Token Index: 281