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

Dataset: Open Web Text

Neuron 374 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: 2.7890. Min Range: -2.7890

Max Act: 2.7890. Min Act: -0.1700

Data Index: 3711334 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.7825. Min Act: -0.1697

Data Index: 38281 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6995. Min Act: -0.1698

Data Index: 2689036 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6821. Min Act: -0.1689

Data Index: 27380 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6687. Min Act: -0.1699

Data Index: 3008710 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6741. Min Act: -0.1700

Data Index: 3478840 (Open Web Text)

Max Activating Token Index: 745

Text #6

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6434. Min Act: -0.1693

Data Index: 7959060 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6338. Min Act: -0.1697

Data Index: 8431628 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6286. Min Act: -0.1636

Data Index: 6189920 (Open Web Text)

Max Activating Token Index: 138

Text #9

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6193. Min Act: -0.1530

Data Index: 2032031 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6235. Min Act: -0.1699

Data Index: 3509053 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6174. Min Act: -0.1698

Data Index: 4809424 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6193. Min Act: -0.1678

Data Index: 1679624 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6050. Min Act: -0.1689

Data Index: 3933275 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.6065. Min Act: -0.1700

Data Index: 8247128 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.5818. Min Act: -0.1675

Data Index: 2162606 (Open Web Text)

Max Activating Token Index: 448

Text #16

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.5865. Min Act: -0.1691

Data Index: 2443987 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.5777. Min Act: -0.1700

Data Index: 2566350 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.5871. Min Act: -0.1657

Data Index: 6484479 (Open Web Text)

Max Activating Token Index: 332

Text #19

Max Range: 2.7890. Min Range: -2.7890

Max Act: 2.5976. Min Act: -0.1698

Data Index: 6701793 (Open Web Text)

Max Activating Token Index: 593