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

Dataset: Open Web Text

Neuron 1289 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: 5.2630. Min Range: -5.2630

Max Act: 5.2630. Min Act: -0.1700

Data Index: 550216 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2386. Min Act: -0.1700

Data Index: 1849456 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2533. Min Act: -0.1700

Data Index: 8674654 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2473. Min Act: -0.1700

Data Index: 693764 (Open Web Text)

Max Activating Token Index: 995

Text #4

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2223. Min Act: -0.1700

Data Index: 1189271 (Open Web Text)

Max Activating Token Index: 354

Text #5

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.2180. Min Act: -0.1700

Data Index: 3288527 (Open Web Text)

Max Activating Token Index: 985

Text #6

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1475. Min Act: -0.1700

Data Index: 3626897 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1546. Min Act: -0.1700

Data Index: 4691832 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1592. Min Act: -0.1700

Data Index: 1434192 (Open Web Text)

Max Activating Token Index: 330

Text #9

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1558. Min Act: -0.1700

Data Index: 8320869 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1619. Min Act: -0.1700

Data Index: 3130565 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1212. Min Act: -0.1700

Data Index: 1594080 (Open Web Text)

Max Activating Token Index: 203

Text #12

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1423. Min Act: -0.1700

Data Index: 7734516 (Open Web Text)

Max Activating Token Index: 615

Text #13

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.0987. Min Act: -0.1700

Data Index: 3336898 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1100. Min Act: -0.1700

Data Index: 4877657 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.0810. Min Act: -0.1700

Data Index: 7276043 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1054. Min Act: -0.1700

Data Index: 2827369 (Open Web Text)

Max Activating Token Index: 272

Text #17

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.0572. Min Act: -0.1700

Data Index: 7794482 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.0809. Min Act: -0.1700

Data Index: 210411 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 5.2630. Min Range: -5.2630

Max Act: 5.1006. Min Act: -0.1700

Data Index: 1079547 (Open Web Text)

Max Activating Token Index: 296