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

Dataset: Open Web Text

Neuron 1291 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: 3.0517. Min Range: -3.0517

Max Act: 3.0517. Min Act: -0.1700

Data Index: 7909474 (Open Web Text)

Max Activating Token Index: 972

Text #1

Max Range: 3.0517. Min Range: -3.0517

Max Act: 3.0106. Min Act: -0.1700

Data Index: 1221785 (Open Web Text)

Max Activating Token Index: 749

Text #2

Max Range: 3.0517. Min Range: -3.0517

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1395733 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 3.0517. Min Range: -3.0517

Max Act: 3.0088. Min Act: -0.1700

Data Index: 4968671 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9670. Min Act: -0.1700

Data Index: 5384396 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9679. Min Act: -0.1700

Data Index: 8268827 (Open Web Text)

Max Activating Token Index: 632

Text #6

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9908. Min Act: -0.1700

Data Index: 4705609 (Open Web Text)

Max Activating Token Index: 535

Text #7

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9641. Min Act: -0.1700

Data Index: 7253781 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9386. Min Act: -0.1700

Data Index: 1813877 (Open Web Text)

Max Activating Token Index: 78

Text #9

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9748. Min Act: -0.1700

Data Index: 7127513 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9533. Min Act: -0.1700

Data Index: 110549 (Open Web Text)

Max Activating Token Index: 545

Text #11

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9451. Min Act: -0.1700

Data Index: 7354585 (Open Web Text)

Max Activating Token Index: 219

Text #12

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9337. Min Act: -0.1700

Data Index: 1240299 (Open Web Text)

Max Activating Token Index: 58

Text #13

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9443. Min Act: -0.1700

Data Index: 7379074 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9241. Min Act: -0.1700

Data Index: 4377128 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9362. Min Act: -0.1700

Data Index: 5976779 (Open Web Text)

Max Activating Token Index: 191

Text #16

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9277. Min Act: -0.1700

Data Index: 4347927 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9411. Min Act: -0.1700

Data Index: 4102718 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9100. Min Act: -0.1700

Data Index: 5418010 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 3.0517. Min Range: -3.0517

Max Act: 2.9143. Min Act: -0.1700

Data Index: 2597062 (Open Web Text)

Max Activating Token Index: 240