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

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

Neuron 867 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.4893. Min Act: -0.1700

Data Index: 198789 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2393. Min Act: -0.1700

Data Index: 292650 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 1215053 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.0831. Min Act: -0.1700

Data Index: 132861 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.0518. Min Act: -0.1700

Data Index: 457948 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.0206. Min Act: -0.1700

Data Index: 1168166 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8956. Min Act: -0.1700

Data Index: 896 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9581. Min Act: -0.1700

Data Index: 124787 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.0518. Min Act: -0.1700

Data Index: 314180 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9893. Min Act: -0.1700

Data Index: 778326 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9893. Min Act: -0.1700

Data Index: 2916 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9581. Min Act: -0.1700

Data Index: 102313 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9268. Min Act: -0.1700

Data Index: 611375 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8956. Min Act: -0.1700

Data Index: 429469 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8956. Min Act: -0.1700

Data Index: 642476 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8956. Min Act: -0.1700

Data Index: 695864 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8643. Min Act: -0.1700

Data Index: 36729 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.9581. Min Act: -0.1700

Data Index: 35245 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.8956. Min Act: -0.1700

Data Index: 792273 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 5.4893. Min Range: -5.4893

Max Act: 4.7706. Min Act: -0.1700

Data Index: 129768 (C4 (Web Text))

Max Activating Token Index: 612