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

Dataset: Open Web Text

Neuron 1918 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: 4.1621. Min Range: -4.1621

Max Act: 4.1621. Min Act: -0.1700

Data Index: 5735223 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1400. Min Act: -0.1700

Data Index: 6161010 (Open Web Text)

Max Activating Token Index: 155

Text #2

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1330. Min Act: -0.1700

Data Index: 2707242 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1200. Min Act: -0.1700

Data Index: 7794564 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0835. Min Act: -0.1700

Data Index: 6706675 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1112. Min Act: -0.1700

Data Index: 7576188 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1116. Min Act: -0.1700

Data Index: 2990351 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0935. Min Act: -0.1700

Data Index: 8706953 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1116. Min Act: -0.1700

Data Index: 7881232 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1311. Min Act: -0.1700

Data Index: 7810712 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1142. Min Act: -0.1700

Data Index: 1767922 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.1081. Min Act: -0.1700

Data Index: 7727592 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0795. Min Act: -0.1700

Data Index: 1196010 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0804. Min Act: -0.1700

Data Index: 5735214 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0804. Min Act: -0.1700

Data Index: 3655914 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0541. Min Act: -0.1700

Data Index: 7122428 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0374. Min Act: -0.1700

Data Index: 572205 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0394. Min Act: -0.1700

Data Index: 7580996 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0463. Min Act: -0.1700

Data Index: 5771780 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 4.1621. Min Range: -4.1621

Max Act: 4.0186. Min Act: -0.1700

Data Index: 2096680 (Open Web Text)

Max Activating Token Index: 66