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

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

Neuron 1793 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: 5.7531. Min Range: -5.7531

Max Act: 5.7531. Min Act: -0.1700

Data Index: 44510 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.7531. Min Act: -0.1700

Data Index: 203948 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.5969. Min Act: -0.1700

Data Index: 769273 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.5656. Min Act: -0.1700

Data Index: 123016 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.5656. Min Act: -0.1700

Data Index: 860516 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.4406. Min Act: -0.1700

Data Index: 1310402 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.4406. Min Act: -0.1700

Data Index: 1029620 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.4094. Min Act: -0.1700

Data Index: 774551 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.4406. Min Act: -0.1700

Data Index: 405062 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.3781. Min Act: -0.1700

Data Index: 9396 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.3781. Min Act: -0.1700

Data Index: 871091 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.3469. Min Act: -0.1700

Data Index: 160497 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2844. Min Act: -0.1700

Data Index: 649776 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2844. Min Act: -0.1700

Data Index: 1154629 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2219. Min Act: -0.1700

Data Index: 662838 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2531. Min Act: -0.1700

Data Index: 77777 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2844. Min Act: -0.1700

Data Index: 157253 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2531. Min Act: -0.1700

Data Index: 923851 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2844. Min Act: -0.1700

Data Index: 788840 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 5.7531. Min Range: -5.7531

Max Act: 5.2531. Min Act: -0.1700

Data Index: 1041638 (C4 (Web Text))

Max Activating Token Index: 741