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

Dataset: Open Web Text

Neuron 2789 in Layer 3

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: 4.3777. Min Range: -4.3777

Max Act: 4.3777. Min Act: -0.1700

Data Index: 5578390 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.3026. Min Act: -0.1700

Data Index: 4358681 (Open Web Text)

Max Activating Token Index: 539

Text #2

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.3382. Min Act: -0.1700

Data Index: 1759997 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.3155. Min Act: -0.1700

Data Index: 1121634 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2736. Min Act: -0.1700

Data Index: 2319166 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2727. Min Act: -0.1700

Data Index: 4688852 (Open Web Text)

Max Activating Token Index: 836

Text #6

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2603. Min Act: -0.1700

Data Index: 4261705 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.3048. Min Act: -0.1700

Data Index: 7536883 (Open Web Text)

Max Activating Token Index: 683

Text #8

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2829. Min Act: -0.1700

Data Index: 5760145 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2318. Min Act: -0.1700

Data Index: 200272 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2402. Min Act: -0.1700

Data Index: 8250781 (Open Web Text)

Max Activating Token Index: 507

Text #11

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2600. Min Act: -0.1700

Data Index: 5649575 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2696. Min Act: -0.1700

Data Index: 5330706 (Open Web Text)

Max Activating Token Index: 448

Text #13

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2623. Min Act: -0.1700

Data Index: 1541101 (Open Web Text)

Max Activating Token Index: 334

Text #14

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2231. Min Act: -0.1700

Data Index: 1130557 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.1989. Min Act: -0.1700

Data Index: 3319266 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2295. Min Act: -0.1700

Data Index: 2539427 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.1975. Min Act: -0.1700

Data Index: 2302139 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.2055. Min Act: -0.1700

Data Index: 8321301 (Open Web Text)

Max Activating Token Index: 441

Text #19

Max Range: 4.3777. Min Range: -4.3777

Max Act: 4.1836. Min Act: -0.1700

Data Index: 738232 (Open Web Text)

Max Activating Token Index: 464