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

Dataset: Open Web Text

Neuron 1489 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: 5.4071. Min Range: -5.4071

Max Act: 5.3944. Min Act: -0.1700

Data Index: 5424391 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3862. Min Act: -0.1700

Data Index: 470740 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.4071. Min Act: -0.1700

Data Index: 8118934 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3548. Min Act: -0.1700

Data Index: 2834566 (Open Web Text)

Max Activating Token Index: 892

Text #4

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3145. Min Act: -0.1700

Data Index: 8216129 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3257. Min Act: -0.1700

Data Index: 2145443 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3115. Min Act: -0.1700

Data Index: 5545203 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2793. Min Act: -0.1700

Data Index: 4447667 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3137. Min Act: -0.1700

Data Index: 7072216 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2766. Min Act: -0.1700

Data Index: 8218633 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2933. Min Act: -0.1700

Data Index: 6302705 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2679. Min Act: -0.1700

Data Index: 7910762 (Open Web Text)

Max Activating Token Index: 655

Text #12

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.3072. Min Act: -0.1700

Data Index: 1415374 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2949. Min Act: -0.1700

Data Index: 525414 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2815. Min Act: -0.1700

Data Index: 2012036 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2703. Min Act: -0.1700

Data Index: 2305520 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2716. Min Act: -0.1700

Data Index: 6424452 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2965. Min Act: -0.1700

Data Index: 7093736 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2474. Min Act: -0.1700

Data Index: 466798 (Open Web Text)

Max Activating Token Index: 661

Text #19

Max Range: 5.4071. Min Range: -5.4071

Max Act: 5.2390. Min Act: -0.1700

Data Index: 4837486 (Open Web Text)

Max Activating Token Index: 386