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

Dataset: Open Web Text

Neuron 454 in Layer 6

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: 6.3304. Min Range: -6.3304

Max Act: 6.3304. Min Act: -0.1700

Data Index: 3787211 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 6.3304. Min Range: -6.3304

Max Act: 6.2331. Min Act: -0.1700

Data Index: 1466268 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 6.3304. Min Range: -6.3304

Max Act: 6.0948. Min Act: -0.1700

Data Index: 8422083 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 6.3304. Min Range: -6.3304

Max Act: 6.0812. Min Act: -0.1700

Data Index: 5355866 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 6.3304. Min Range: -6.3304

Max Act: 6.0576. Min Act: -0.1699

Data Index: 8150788 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.9807. Min Act: -0.1699

Data Index: 8437844 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.9396. Min Act: -0.1700

Data Index: 3839259 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.9463. Min Act: -0.1700

Data Index: 5658754 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.9496. Min Act: -0.1700

Data Index: 3213800 (Open Web Text)

Max Activating Token Index: 955

Text #9

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.9343. Min Act: -0.1700

Data Index: 8324731 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.8851. Min Act: -0.1700

Data Index: 352259 (Open Web Text)

Max Activating Token Index: 718

Text #11

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.8792. Min Act: -0.1699

Data Index: 881908 (Open Web Text)

Max Activating Token Index: 778

Text #12

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.7668. Min Act: -0.1700

Data Index: 2983692 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.7336. Min Act: -0.1700

Data Index: 5804233 (Open Web Text)

Max Activating Token Index: 958

Text #14

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.6241. Min Act: -0.1697

Data Index: 3392526 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.6520. Min Act: -0.1700

Data Index: 6943580 (Open Web Text)

Max Activating Token Index: 461

Text #16

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.6458. Min Act: -0.1700

Data Index: 7935987 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.6252. Min Act: -0.1700

Data Index: 3644695 (Open Web Text)

Max Activating Token Index: 398

Text #18

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.5955. Min Act: -0.1700

Data Index: 6617924 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 6.3304. Min Range: -6.3304

Max Act: 5.6464. Min Act: -0.1700

Data Index: 7236649 (Open Web Text)

Max Activating Token Index: 562