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

Dataset: Open Web Text

Neuron 351 in Layer 5

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: 4.2395. Min Range: -4.2395

Max Act: 4.2395. Min Act: -0.1700

Data Index: 38133 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1700. Min Act: -0.1700

Data Index: 6661767 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1700. Min Act: -0.1700

Data Index: 8093635 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1386. Min Act: -0.1700

Data Index: 4767253 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1738. Min Act: -0.1700

Data Index: 353656 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0974. Min Act: -0.1700

Data Index: 8115226 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0905. Min Act: -0.1700

Data Index: 6790274 (Open Web Text)

Max Activating Token Index: 997

Text #7

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1119. Min Act: -0.1700

Data Index: 1034683 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1221. Min Act: -0.1700

Data Index: 1017209 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0655. Min Act: -0.1700

Data Index: 6607600 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1311. Min Act: -0.1700

Data Index: 6563399 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1030. Min Act: -0.1700

Data Index: 5646492 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0997. Min Act: -0.1700

Data Index: 2633628 (Open Web Text)

Max Activating Token Index: 573

Text #13

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0745. Min Act: -0.1700

Data Index: 5318541 (Open Web Text)

Max Activating Token Index: 620

Text #14

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0289. Min Act: -0.1700

Data Index: 5182404 (Open Web Text)

Max Activating Token Index: 777

Text #15

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0832. Min Act: -0.1700

Data Index: 4879923 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0952. Min Act: -0.1700

Data Index: 2205992 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.0616. Min Act: -0.1700

Data Index: 7222730 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1246. Min Act: -0.1700

Data Index: 7242040 (Open Web Text)

Max Activating Token Index: 733

Text #19

Max Range: 4.2395. Min Range: -4.2395

Max Act: 4.1047. Min Act: -0.1700

Data Index: 2932519 (Open Web Text)

Max Activating Token Index: 570