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

Dataset: Open Web Text

Neuron 14 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: 4.6451. Min Range: -4.6451

Max Act: 4.6451. Min Act: -0.1700

Data Index: 4497004 (Open Web Text)

Max Activating Token Index: 312

Text #1

Max Range: 4.6451. Min Range: -4.6451

Max Act: 4.3488. Min Act: -0.1700

Data Index: 4500258 (Open Web Text)

Max Activating Token Index: 847

Text #2

Max Range: 4.6451. Min Range: -4.6451

Max Act: 4.2351. Min Act: -0.1700

Data Index: 6837296 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 4.6451. Min Range: -4.6451

Max Act: 4.1242. Min Act: -0.1700

Data Index: 3919860 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 4.6451. Min Range: -4.6451

Max Act: 4.0667. Min Act: -0.1700

Data Index: 6971298 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 4.6451. Min Range: -4.6451

Max Act: 4.0269. Min Act: -0.1700

Data Index: 4252311 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.9366. Min Act: -0.1700

Data Index: 4668911 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.8641. Min Act: -0.1700

Data Index: 4567195 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.7599. Min Act: -0.1700

Data Index: 4825519 (Open Web Text)

Max Activating Token Index: 885

Text #9

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.7520. Min Act: -0.1700

Data Index: 2298581 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6824. Min Act: -0.1700

Data Index: 5812804 (Open Web Text)

Max Activating Token Index: 812

Text #11

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.7251. Min Act: -0.1700

Data Index: 5924239 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.7039. Min Act: -0.1700

Data Index: 2341559 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.7427. Min Act: -0.1700

Data Index: 7114550 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6708. Min Act: -0.1700

Data Index: 8580807 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6900. Min Act: -0.1700

Data Index: 2057953 (Open Web Text)

Max Activating Token Index: 935

Text #16

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6487. Min Act: -0.1700

Data Index: 3349239 (Open Web Text)

Max Activating Token Index: 551

Text #17

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6545. Min Act: -0.1700

Data Index: 6345122 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.6515. Min Act: -0.1700

Data Index: 2527178 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 4.6451. Min Range: -4.6451

Max Act: 3.5984. Min Act: -0.1700

Data Index: 4296079 (Open Web Text)

Max Activating Token Index: 545