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

Dataset: Open Web Text

Neuron 472 in Layer 0

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: 1.7963. Min Range: -1.7963

Max Act: 1.7893. Min Act: -0.1684

Data Index: 3551228 (Open Web Text)

Max Activating Token Index: 558

Text #1

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7963. Min Act: -0.1700

Data Index: 2319229 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7827. Min Act: -0.1694

Data Index: 4524156 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7817. Min Act: -0.1700

Data Index: 2468606 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7760. Min Act: -0.1700

Data Index: 5220498 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7702. Min Act: -0.1698

Data Index: 199502 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7729. Min Act: -0.1700

Data Index: 3914602 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7529. Min Act: -0.1700

Data Index: 32889 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7530. Min Act: -0.1641

Data Index: 315724 (Open Web Text)

Max Activating Token Index: 420

Text #9

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7428. Min Act: -0.1700

Data Index: 5608827 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7466. Min Act: -0.1697

Data Index: 4376379 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7508. Min Act: -0.1700

Data Index: 1275879 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7462. Min Act: -0.1700

Data Index: 298574 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7428. Min Act: -0.1700

Data Index: 8700681 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7462. Min Act: -0.1695

Data Index: 5823950 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7427. Min Act: -0.1699

Data Index: 4127108 (Open Web Text)

Max Activating Token Index: 815

Text #16

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7319. Min Act: -0.1699

Data Index: 1234303 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7361. Min Act: -0.1690

Data Index: 709253 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7309. Min Act: -0.1700

Data Index: 3699347 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 1.7963. Min Range: -1.7963

Max Act: 1.7355. Min Act: -0.1700

Data Index: 72806 (Open Web Text)

Max Activating Token Index: 304