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

Dataset: Open Web Text

Neuron 998 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: 3.4537. Min Range: -3.4537

Max Act: 3.4537. Min Act: -0.1700

Data Index: 4887011 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3946. Min Act: -0.1700

Data Index: 677277 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3412. Min Act: -0.1700

Data Index: 6179007 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3196. Min Act: -0.1700

Data Index: 7435641 (Open Web Text)

Max Activating Token Index: 739

Text #4

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3552. Min Act: -0.1700

Data Index: 4040274 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3031. Min Act: -0.1700

Data Index: 195615 (Open Web Text)

Max Activating Token Index: 390

Text #6

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3267. Min Act: -0.1700

Data Index: 3843551 (Open Web Text)

Max Activating Token Index: 880

Text #7

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3348. Min Act: -0.1700

Data Index: 2144386 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.3036. Min Act: -0.1700

Data Index: 1457506 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2576. Min Act: -0.1700

Data Index: 3556638 (Open Web Text)

Max Activating Token Index: 848

Text #10

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2608. Min Act: -0.1700

Data Index: 5168797 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2604. Min Act: -0.1700

Data Index: 7877011 (Open Web Text)

Max Activating Token Index: 562

Text #12

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2471. Min Act: -0.1700

Data Index: 2624507 (Open Web Text)

Max Activating Token Index: 967

Text #13

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2148. Min Act: -0.1700

Data Index: 7654686 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2384. Min Act: -0.1700

Data Index: 6967184 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2541. Min Act: -0.1700

Data Index: 4615687 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2415. Min Act: -0.1700

Data Index: 2142601 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2143. Min Act: -0.1700

Data Index: 6416985 (Open Web Text)

Max Activating Token Index: 340

Text #18

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2434. Min Act: -0.1700

Data Index: 1186881 (Open Web Text)

Max Activating Token Index: 313

Text #19

Max Range: 3.4537. Min Range: -3.4537

Max Act: 3.2314. Min Act: -0.1700

Data Index: 7260761 (Open Web Text)

Max Activating Token Index: 363