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

Dataset: Open Web Text

Neuron 1953 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: 3.8707. Min Range: -3.8707

Max Act: 3.8707. Min Act: -0.1700

Data Index: 4032822 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.8629. Min Act: -0.1700

Data Index: 4393060 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.8214. Min Act: -0.1700

Data Index: 8181107 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.8203. Min Act: -0.1700

Data Index: 1828427 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7846. Min Act: -0.1700

Data Index: 4933520 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.8105. Min Act: -0.1700

Data Index: 6109067 (Open Web Text)

Max Activating Token Index: 770

Text #6

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7522. Min Act: -0.1700

Data Index: 8235087 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7728. Min Act: -0.1700

Data Index: 5283681 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7456. Min Act: -0.1700

Data Index: 1764927 (Open Web Text)

Max Activating Token Index: 436

Text #9

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7594. Min Act: -0.1700

Data Index: 2287677 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7436. Min Act: -0.1700

Data Index: 4696269 (Open Web Text)

Max Activating Token Index: 851

Text #11

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7503. Min Act: -0.1700

Data Index: 5884675 (Open Web Text)

Max Activating Token Index: 631

Text #12

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7450. Min Act: -0.1700

Data Index: 4576563 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7423. Min Act: -0.1700

Data Index: 8000943 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7468. Min Act: -0.1700

Data Index: 8326683 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7194. Min Act: -0.1700

Data Index: 5252282 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7361. Min Act: -0.1700

Data Index: 4951192 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7188. Min Act: -0.1700

Data Index: 326374 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1283493 (Open Web Text)

Max Activating Token Index: 586

Text #19

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7142. Min Act: -0.1700

Data Index: 5485766 (Open Web Text)

Max Activating Token Index: 83