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

Dataset: Open Web Text

Neuron 289 in Layer 1

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: 4.4479. Min Range: -4.4479

Max Act: 4.4479. Min Act: -0.1696

Data Index: 8389407 (Open Web Text)

Max Activating Token Index: 476

Text #1

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.2480. Min Act: -0.1700

Data Index: 5588516 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0879. Min Act: -0.1571

Data Index: 6232300 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.1081. Min Act: -0.1697

Data Index: 7735376 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0185. Min Act: -0.1700

Data Index: 6613489 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0377. Min Act: -0.1700

Data Index: 6392005 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0479. Min Act: -0.1700

Data Index: 58774 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9848. Min Act: -0.1700

Data Index: 4594969 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0033. Min Act: -0.1700

Data Index: 5814237 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 4.4479. Min Range: -4.4479

Max Act: 4.0183. Min Act: -0.1700

Data Index: 1242564 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9683. Min Act: -0.1700

Data Index: 4123589 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9648. Min Act: -0.1700

Data Index: 3897715 (Open Web Text)

Max Activating Token Index: 745

Text #12

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9357. Min Act: -0.1700

Data Index: 3926300 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9286. Min Act: -0.1691

Data Index: 911406 (Open Web Text)

Max Activating Token Index: 387

Text #14

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9372. Min Act: -0.1662

Data Index: 4247081 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9208. Min Act: -0.1699

Data Index: 7368335 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9428. Min Act: -0.1700

Data Index: 8350017 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9171. Min Act: -0.1700

Data Index: 8772745 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9048. Min Act: -0.1689

Data Index: 2759279 (Open Web Text)

Max Activating Token Index: 818

Text #19

Max Range: 4.4479. Min Range: -4.4479

Max Act: 3.9066. Min Act: -0.1700

Data Index: 818489 (Open Web Text)

Max Activating Token Index: 870