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

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

Neuron 957 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.3411. Min Act: -0.1700

Data Index: 1505144 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2318. Min Act: -0.1700

Data Index: 1223389 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2005. Min Act: -0.1700

Data Index: 98122 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2474. Min Act: -0.1700

Data Index: 586702 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2318. Min Act: -0.1700

Data Index: 184959 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2630. Min Act: -0.1700

Data Index: 1332101 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2474. Min Act: -0.1700

Data Index: 1420133 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2161. Min Act: -0.1700

Data Index: 1134184 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2318. Min Act: -0.1700

Data Index: 981120 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1849. Min Act: -0.1700

Data Index: 1132619 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2474. Min Act: -0.1700

Data Index: 103336 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1693. Min Act: -0.1700

Data Index: 929497 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1536. Min Act: -0.1700

Data Index: 537692 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1380. Min Act: -0.1700

Data Index: 637549 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1068. Min Act: -0.1700

Data Index: 1112360 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1380. Min Act: -0.1700

Data Index: 1060567 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.1068. Min Act: -0.1700

Data Index: 1307465 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2318. Min Act: -0.1700

Data Index: 189971 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.2318. Min Act: -0.1700

Data Index: 1030770 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 5.3411. Min Range: -5.3411

Max Act: 5.0911. Min Act: -0.1700

Data Index: 1021071 (C4 (Web Text))

Max Activating Token Index: 51