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

Dataset: Open Web Text

Neuron 1698 in Layer 5

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: 3.3543. Min Range: -3.3543

Max Act: 3.3543. Min Act: -0.1700

Data Index: 2406626 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.3084. Min Act: -0.1700

Data Index: 176589 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.2528. Min Act: -0.1700

Data Index: 6231774 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1644. Min Act: -0.1700

Data Index: 6002795 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1355. Min Act: -0.1700

Data Index: 3128636 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1286. Min Act: -0.1700

Data Index: 2084747 (Open Web Text)

Max Activating Token Index: 309

Text #6

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1348. Min Act: -0.1700

Data Index: 2382916 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1133. Min Act: -0.1700

Data Index: 8600678 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1213. Min Act: -0.1700

Data Index: 340953 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0793. Min Act: -0.1700

Data Index: 3111735 (Open Web Text)

Max Activating Token Index: 166

Text #10

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1069. Min Act: -0.1700

Data Index: 3261531 (Open Web Text)

Max Activating Token Index: 310

Text #11

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0952. Min Act: -0.1700

Data Index: 4848865 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.1054. Min Act: -0.1700

Data Index: 6556751 (Open Web Text)

Max Activating Token Index: 714

Text #13

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0730. Min Act: -0.1700

Data Index: 7338804 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0644. Min Act: -0.1700

Data Index: 6464219 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0488. Min Act: -0.1700

Data Index: 7005666 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0678. Min Act: -0.1700

Data Index: 4913691 (Open Web Text)

Max Activating Token Index: 337

Text #17

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0307. Min Act: -0.1700

Data Index: 2928108 (Open Web Text)

Max Activating Token Index: 781

Text #18

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0407. Min Act: -0.1700

Data Index: 5439131 (Open Web Text)

Max Activating Token Index: 301

Text #19

Max Range: 3.3543. Min Range: -3.3543

Max Act: 3.0418. Min Act: -0.1700

Data Index: 6957134 (Open Web Text)

Max Activating Token Index: 76