Model: None

Dataset: The Pile

Neuron 2454 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')

Text #0

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.3390. Min Act: -0.1700

Data Index: 1568581 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 5.3390. Min Range: -5.3390

Max Act: 5.1203. Min Act: -0.1700

Data Index: 10018374 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.9328. Min Act: -0.1700

Data Index: 9372735 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.6202. Min Act: -0.1700

Data Index: 5000817 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.5577. Min Act: -0.1700

Data Index: 6761754 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.5265. Min Act: -0.1700

Data Index: 7792866 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4952. Min Act: -0.1700

Data Index: 9564213 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4952. Min Act: -0.1700

Data Index: 10672275 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4640. Min Act: -0.1700

Data Index: 3681546 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4640. Min Act: -0.1700

Data Index: 8096706 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4327. Min Act: -0.1700

Data Index: 7455483 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4015. Min Act: -0.1700

Data Index: 10546491 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.4015. Min Act: -0.1700

Data Index: 3113087 (The Pile)

Max Activating Token Index: 892

Text #13

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.3390. Min Act: -0.1700

Data Index: 3267543 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.3390. Min Act: -0.1700

Data Index: 7588377 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.3077. Min Act: -0.1700

Data Index: 1128988 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.2765. Min Act: -0.1700

Data Index: 32640 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.2765. Min Act: -0.1700

Data Index: 6002370 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.2452. Min Act: -0.1700

Data Index: 358494 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 5.3390. Min Range: -5.3390

Max Act: 4.2452. Min Act: -0.1700

Data Index: 8660664 (The Pile)

Max Activating Token Index: 272