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

Dataset: Open Web Text

Neuron 1 in Layer 4

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: 5.6793. Min Range: -5.6793

Max Act: 5.6793. Min Act: -0.1700

Data Index: 6715550 (Open Web Text)

Max Activating Token Index: 926

Text #1

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.5252. Min Act: -0.1700

Data Index: 1941870 (Open Web Text)

Max Activating Token Index: 559

Text #2

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.4347. Min Act: -0.1700

Data Index: 2168456 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.4375. Min Act: -0.1700

Data Index: 3030175 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.4110. Min Act: -0.1700

Data Index: 8333637 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.3615. Min Act: -0.1700

Data Index: 7711857 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.3474. Min Act: -0.1700

Data Index: 7301889 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.2389. Min Act: -0.1700

Data Index: 5080614 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.2676. Min Act: -0.1700

Data Index: 7964072 (Open Web Text)

Max Activating Token Index: 449

Text #9

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.2472. Min Act: -0.1700

Data Index: 1394225 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1976. Min Act: -0.1700

Data Index: 8401712 (Open Web Text)

Max Activating Token Index: 286

Text #11

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.0893. Min Act: -0.1700

Data Index: 584832 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1727. Min Act: -0.1700

Data Index: 7505299 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1439. Min Act: -0.1700

Data Index: 542681 (Open Web Text)

Max Activating Token Index: 426

Text #14

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1613. Min Act: -0.1700

Data Index: 5881392 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1565. Min Act: -0.1700

Data Index: 7798572 (Open Web Text)

Max Activating Token Index: 384

Text #16

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.0846. Min Act: -0.1700

Data Index: 8271433 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.0479. Min Act: -0.1700

Data Index: 380482 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.1081. Min Act: -0.1700

Data Index: 2312801 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 5.6793. Min Range: -5.6793

Max Act: 5.0598. Min Act: -0.1700

Data Index: 4859169 (Open Web Text)

Max Activating Token Index: 831