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

Dataset: Open Web Text

Neuron 1156 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: 5.8397. Min Range: -5.8397

Max Act: 5.8397. Min Act: -0.1700

Data Index: 8074992 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.4372. Min Act: -0.1700

Data Index: 4076404 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.4394. Min Act: -0.1700

Data Index: 4996508 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.4122. Min Act: -0.1700

Data Index: 8226542 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.3524. Min Act: -0.1700

Data Index: 1006864 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.3066. Min Act: -0.1700

Data Index: 1070428 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.3041. Min Act: -0.1700

Data Index: 7613188 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2464. Min Act: -0.1700

Data Index: 5031598 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2797. Min Act: -0.1699

Data Index: 1745261 (Open Web Text)

Max Activating Token Index: 401

Text #9

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1986. Min Act: -0.1700

Data Index: 237233 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2504. Min Act: -0.1700

Data Index: 6784785 (Open Web Text)

Max Activating Token Index: 364

Text #11

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2514. Min Act: -0.1700

Data Index: 3977223 (Open Web Text)

Max Activating Token Index: 430

Text #12

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1985. Min Act: -0.1700

Data Index: 6895205 (Open Web Text)

Max Activating Token Index: 919

Text #13

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2037. Min Act: -0.1700

Data Index: 8199409 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2187. Min Act: -0.1700

Data Index: 7863171 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1646. Min Act: -0.1700

Data Index: 3841882 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.2071. Min Act: -0.1700

Data Index: 4362611 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1534. Min Act: -0.1700

Data Index: 4311913 (Open Web Text)

Max Activating Token Index: 919

Text #18

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1480. Min Act: -0.1700

Data Index: 6325695 (Open Web Text)

Max Activating Token Index: 229

Text #19

Max Range: 5.8397. Min Range: -5.8397

Max Act: 5.1442. Min Act: -0.1700

Data Index: 7599256 (Open Web Text)

Max Activating Token Index: 935