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

Dataset: Open Web Text

Neuron 1782 in Layer 1

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: 3.6393. Min Range: -3.6393

Max Act: 3.6393. Min Act: -0.1700

Data Index: 1434422 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5794. Min Act: -0.1700

Data Index: 8370392 (Open Web Text)

Max Activating Token Index: 571

Text #2

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5695. Min Act: -0.1700

Data Index: 4638136 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.6016. Min Act: -0.1700

Data Index: 4458437 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5591. Min Act: -0.1700

Data Index: 2751798 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5463. Min Act: -0.1700

Data Index: 7838063 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5578. Min Act: -0.1700

Data Index: 4957117 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5192. Min Act: -0.1700

Data Index: 6010467 (Open Web Text)

Max Activating Token Index: 399

Text #8

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5044. Min Act: -0.1700

Data Index: 5683509 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5230. Min Act: -0.1700

Data Index: 2632644 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5168. Min Act: -0.1700

Data Index: 7190513 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5137. Min Act: -0.1700

Data Index: 3930195 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.5033. Min Act: -0.1700

Data Index: 4591731 (Open Web Text)

Max Activating Token Index: 409

Text #13

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4961. Min Act: -0.1700

Data Index: 8803103 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4866. Min Act: -0.1700

Data Index: 203646 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4775. Min Act: -0.1700

Data Index: 6399371 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4889. Min Act: -0.1700

Data Index: 6545171 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4923. Min Act: -0.1700

Data Index: 2298044 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4847. Min Act: -0.1700

Data Index: 2463183 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 3.6393. Min Range: -3.6393

Max Act: 3.4928. Min Act: -0.1700

Data Index: 4470905 (Open Web Text)

Max Activating Token Index: 527