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

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

Neuron 1114 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1505962 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6959. Min Act: -0.1700

Data Index: 3822 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6959. Min Act: -0.1700

Data Index: 1612935 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6959. Min Act: -0.1700

Data Index: 1619177 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6959. Min Act: -0.1700

Data Index: 1444860 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6802. Min Act: -0.1700

Data Index: 737935 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6802. Min Act: -0.1700

Data Index: 1539763 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6646. Min Act: -0.1700

Data Index: 592438 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6333. Min Act: -0.1700

Data Index: 744213 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6489. Min Act: -0.1700

Data Index: 1153068 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6019. Min Act: -0.1700

Data Index: 476753 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6019. Min Act: -0.1700

Data Index: 635040 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5863. Min Act: -0.1700

Data Index: 920112 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6019. Min Act: -0.1700

Data Index: 337164 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5863. Min Act: -0.1700

Data Index: 31488 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.6176. Min Act: -0.1700

Data Index: 1201788 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5863. Min Act: -0.1700

Data Index: 1267398 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5863. Min Act: -0.1700

Data Index: 642796 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5863. Min Act: -0.1700

Data Index: 1108917 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 3.7897. Min Range: -3.7897

Max Act: 3.5706. Min Act: -0.1700

Data Index: 863372 (C4 (Web Text))

Max Activating Token Index: 445