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

Dataset: Open Web Text

Neuron 1791 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: 2.6802. Min Range: -2.6802

Max Act: 2.6802. Min Act: -0.1700

Data Index: 8030831 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.6292. Min Act: -0.1700

Data Index: 4992414 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5805. Min Act: -0.1700

Data Index: 4846198 (Open Web Text)

Max Activating Token Index: 328

Text #3

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5682. Min Act: -0.1700

Data Index: 4574976 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5868. Min Act: -0.1700

Data Index: 3751484 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5571. Min Act: -0.1700

Data Index: 4557347 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5728. Min Act: -0.1700

Data Index: 15753 (Open Web Text)

Max Activating Token Index: 196

Text #7

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5093. Min Act: -0.1700

Data Index: 1371451 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5028. Min Act: -0.1700

Data Index: 1076544 (Open Web Text)

Max Activating Token Index: 691

Text #9

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4915. Min Act: -0.1700

Data Index: 4055616 (Open Web Text)

Max Activating Token Index: 290

Text #10

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4588. Min Act: -0.1700

Data Index: 7361493 (Open Web Text)

Max Activating Token Index: 49

Text #11

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4719. Min Act: -0.1700

Data Index: 1844495 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4659. Min Act: -0.1700

Data Index: 4645696 (Open Web Text)

Max Activating Token Index: 400

Text #13

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4759. Min Act: -0.1700

Data Index: 3605291 (Open Web Text)

Max Activating Token Index: 984

Text #14

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4556. Min Act: -0.1700

Data Index: 3605302 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4323. Min Act: -0.1700

Data Index: 1661830 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4449. Min Act: -0.1700

Data Index: 1501350 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4447. Min Act: -0.1700

Data Index: 6022170 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4439. Min Act: -0.1700

Data Index: 3324137 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4324. Min Act: -0.1700

Data Index: 5968286 (Open Web Text)

Max Activating Token Index: 235