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

Dataset: Open Web Text

Neuron 622 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: 5.8778. Min Range: -5.8778

Max Act: 5.8778. Min Act: -0.1700

Data Index: 3564758 (Open Web Text)

Max Activating Token Index: 571

Text #1

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.6060. Min Act: -0.1700

Data Index: 7494313 (Open Web Text)

Max Activating Token Index: 966

Text #2

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.3561. Min Act: -0.1700

Data Index: 4291823 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.3874. Min Act: -0.1700

Data Index: 1201115 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.3733. Min Act: -0.1700

Data Index: 8365068 (Open Web Text)

Max Activating Token Index: 512

Text #5

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.2362. Min Act: -0.1700

Data Index: 7253463 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.2244. Min Act: -0.1700

Data Index: 7106638 (Open Web Text)

Max Activating Token Index: 284

Text #7

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1736. Min Act: -0.1700

Data Index: 5080578 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1006. Min Act: -0.1700

Data Index: 3890873 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.0803. Min Act: -0.1700

Data Index: 6081510 (Open Web Text)

Max Activating Token Index: 450

Text #10

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1782. Min Act: -0.1700

Data Index: 8221170 (Open Web Text)

Max Activating Token Index: 971

Text #11

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1356. Min Act: -0.1700

Data Index: 8365069 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1344. Min Act: -0.1700

Data Index: 1227931 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1133. Min Act: -0.1700

Data Index: 6451487 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.0631. Min Act: -0.1700

Data Index: 2538843 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.1050. Min Act: -0.1700

Data Index: 2967914 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 5.8778. Min Range: -5.8778

Max Act: 4.9844. Min Act: -0.1700

Data Index: 591761 (Open Web Text)

Max Activating Token Index: 289

Text #17

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.0446. Min Act: -0.1700

Data Index: 3748529 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.0809. Min Act: -0.1700

Data Index: 2453234 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 5.8778. Min Range: -5.8778

Max Act: 5.0501. Min Act: -0.1700

Data Index: 7039354 (Open Web Text)

Max Activating Token Index: 237