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

Dataset: Open Web Text

Neuron 2046 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: 3.4929. Min Range: -3.4929

Max Act: 3.4929. Min Act: -0.1700

Data Index: 5909228 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.4408. Min Act: -0.1700

Data Index: 4734481 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.4520. Min Act: -0.1700

Data Index: 3293981 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3422. Min Act: -0.1700

Data Index: 8501106 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3216. Min Act: -0.1700

Data Index: 4895391 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.3072. Min Act: -0.1700

Data Index: 5529908 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2749. Min Act: -0.1700

Data Index: 1716532 (Open Web Text)

Max Activating Token Index: 310

Text #7

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2682. Min Act: -0.1700

Data Index: 5686102 (Open Web Text)

Max Activating Token Index: 725

Text #8

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2758. Min Act: -0.1700

Data Index: 4499606 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2433. Min Act: -0.1700

Data Index: 2308128 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2600. Min Act: -0.1700

Data Index: 1181492 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1479394 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2723. Min Act: -0.1700

Data Index: 4003012 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2510. Min Act: -0.1700

Data Index: 7702392 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2304. Min Act: -0.1700

Data Index: 4719300 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1948954 (Open Web Text)

Max Activating Token Index: 651

Text #16

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2408. Min Act: -0.1700

Data Index: 1691620 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2401. Min Act: -0.1700

Data Index: 3972085 (Open Web Text)

Max Activating Token Index: 210

Text #18

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2196. Min Act: -0.1700

Data Index: 7361033 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.2312. Min Act: -0.1700

Data Index: 6180987 (Open Web Text)

Max Activating Token Index: 217