Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3643. Min Act: -0.1700

Data Index: 937769 (Open Web Text)

Max Activating Token Index: 371

Text #1

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3316. Min Act: -0.1700

Data Index: 6089678 (Open Web Text)

Max Activating Token Index: 936

Text #2

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3377. Min Act: -0.1700

Data Index: 5533886 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3052. Min Act: -0.1700

Data Index: 2135841 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2852. Min Act: -0.1700

Data Index: 6498439 (Open Web Text)

Max Activating Token Index: 594

Text #5

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2795. Min Act: -0.1700

Data Index: 6234197 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2637. Min Act: -0.1700

Data Index: 4285624 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2534. Min Act: -0.1700

Data Index: 6939350 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2648. Min Act: -0.1700

Data Index: 8731652 (Open Web Text)

Max Activating Token Index: 706

Text #9

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2530. Min Act: -0.1700

Data Index: 3456903 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2092. Min Act: -0.1700

Data Index: 3416620 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1727. Min Act: -0.1700

Data Index: 3707682 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1563. Min Act: -0.1700

Data Index: 3712787 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1965. Min Act: -0.1700

Data Index: 1518051 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2062. Min Act: -0.1700

Data Index: 8832420 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2096. Min Act: -0.1700

Data Index: 2046464 (Open Web Text)

Max Activating Token Index: 765

Text #16

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1545. Min Act: -0.1700

Data Index: 8788514 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1596. Min Act: -0.1700

Data Index: 750525 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1641. Min Act: -0.1700

Data Index: 8149008 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1419. Min Act: -0.1700

Data Index: 4019745 (Open Web Text)

Max Activating Token Index: 466