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

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

Neuron 1413 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1063387 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.6223. Min Act: -0.1700

Data Index: 1188837 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5909. Min Act: -0.1700

Data Index: 253556 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5596. Min Act: -0.1700

Data Index: 865560 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5596. Min Act: -0.1700

Data Index: 838466 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1153952 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5596. Min Act: -0.1700

Data Index: 1088583 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5909. Min Act: -0.1700

Data Index: 140588 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 941377 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 449600 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.4970. Min Act: -0.1700

Data Index: 853816 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 9652 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 759854 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 90269 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1030764 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.5283. Min Act: -0.1700

Data Index: 635787 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.4970. Min Act: -0.1700

Data Index: 688425 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.4970. Min Act: -0.1700

Data Index: 763134 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.4970. Min Act: -0.1700

Data Index: 817884 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 3.6536. Min Range: -3.6536

Max Act: 3.4970. Min Act: -0.1700

Data Index: 226723 (C4 (Web Text))

Max Activating Token Index: 225