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

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

Neuron 1876 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: 3.1706. Min Range: -3.1706

Max Act: 3.1706. Min Act: -0.1700

Data Index: 981257 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.1706. Min Range: -3.1706

Max Act: 3.0129. Min Act: -0.1700

Data Index: 872792 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9655. Min Act: -0.1700

Data Index: 802634 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9813. Min Act: -0.1700

Data Index: 1076303 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.1706. Min Range: -3.1706

Max Act: 3.0287. Min Act: -0.1700

Data Index: 199770 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9655. Min Act: -0.1700

Data Index: 770755 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9496. Min Act: -0.1700

Data Index: 1300040 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9496. Min Act: -0.1700

Data Index: 498025 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9496. Min Act: -0.1700

Data Index: 1157061 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9021. Min Act: -0.1700

Data Index: 189684 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9338. Min Act: -0.1700

Data Index: 772906 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9496. Min Act: -0.1700

Data Index: 100671 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9338. Min Act: -0.1700

Data Index: 851389 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.8704. Min Act: -0.1700

Data Index: 799617 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9021. Min Act: -0.1700

Data Index: 421673 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9021. Min Act: -0.1700

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9338. Min Act: -0.1700

Data Index: 587580 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9180. Min Act: -0.1700

Data Index: 1322078 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.9021. Min Act: -0.1700

Data Index: 887811 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 3.1706. Min Range: -3.1706

Max Act: 2.8545. Min Act: -0.1700

Data Index: 1027943 (C4 (Web Text))

Max Activating Token Index: 622