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

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

Neuron 390 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: 5.4060. Min Range: -5.4060

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1076853 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.3435. Min Act: -0.1700

Data Index: 690551 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.2498. Min Act: -0.1700

Data Index: 1337077 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.2810. Min Act: -0.1700

Data Index: 654081 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.3123. Min Act: -0.1700

Data Index: 1040454 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.2185. Min Act: -0.1700

Data Index: 1254535 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.2185. Min Act: -0.1700

Data Index: 1146492 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.2498. Min Act: -0.1700

Data Index: 917200 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 654041 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 453265 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1248. Min Act: -0.1700

Data Index: 657584 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 1297128 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1248. Min Act: -0.1700

Data Index: 750668 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1248. Min Act: -0.1700

Data Index: 1321696 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 182191 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1248. Min Act: -0.1700

Data Index: 1331576 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.1560. Min Act: -0.1700

Data Index: 944085 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.0935. Min Act: -0.1700

Data Index: 750779 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 5.4060. Min Range: -5.4060

Max Act: 5.0310. Min Act: -0.1700

Data Index: 1050895 (C4 (Web Text))

Max Activating Token Index: 966