Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 899 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.1601. Min Act: -0.1700

Data Index: 71849 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0664. Min Act: -0.1700

Data Index: 914573 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0976. Min Act: -0.1700

Data Index: 392693 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0976. Min Act: -0.1700

Data Index: 187334 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0664. Min Act: -0.1700

Data Index: 856240 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0351. Min Act: -0.1700

Data Index: 772740 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0664. Min Act: -0.1700

Data Index: 1353213 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9726. Min Act: -0.1700

Data Index: 476759 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 5.1601. Min Range: -5.1601

Max Act: 5.0351. Min Act: -0.1700

Data Index: 757215 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9726. Min Act: -0.1700

Data Index: 167165 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9414. Min Act: -0.1700

Data Index: 1303778 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9726. Min Act: -0.1700

Data Index: 683663 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9414. Min Act: -0.1700

Data Index: 146899 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9726. Min Act: -0.1700

Data Index: 434053 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.9414. Min Act: -0.1700

Data Index: 841013 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.8789. Min Act: -0.1700

Data Index: 443947 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.8476. Min Act: -0.1700

Data Index: 1106621 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.8164. Min Act: -0.1700

Data Index: 990531 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.8476. Min Act: -0.1700

Data Index: 1265425 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 5.1601. Min Range: -5.1601

Max Act: 4.7851. Min Act: -0.1700

Data Index: 351302 (C4 (Web Text))

Max Activating Token Index: 358