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

Dataset: Open Web Text

Neuron 2123 in Layer 2

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: 1.9256. Min Range: -1.9256

Max Act: 1.9256. Min Act: -0.1691

Data Index: 3342028 (Open Web Text)

Max Activating Token Index: 367

Text #1

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.9108. Min Act: -0.1700

Data Index: 7238621 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8819. Min Act: -0.1700

Data Index: 5403532 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8838. Min Act: -0.1700

Data Index: 4910503 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8517. Min Act: -0.1700

Data Index: 6639854 (Open Web Text)

Max Activating Token Index: 510

Text #5

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8315. Min Act: -0.1700

Data Index: 3904393 (Open Web Text)

Max Activating Token Index: 892

Text #6

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8457. Min Act: -0.1700

Data Index: 5775718 (Open Web Text)

Max Activating Token Index: 161

Text #7

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8297. Min Act: -0.1700

Data Index: 3909058 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8394. Min Act: -0.1700

Data Index: 2182605 (Open Web Text)

Max Activating Token Index: 731

Text #9

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8441. Min Act: -0.1699

Data Index: 6228215 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8282. Min Act: -0.1700

Data Index: 613726 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8219. Min Act: -0.1700

Data Index: 6624676 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8277. Min Act: -0.1700

Data Index: 5713678 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8273. Min Act: -0.1700

Data Index: 3358772 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8105. Min Act: -0.1700

Data Index: 7897640 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8096. Min Act: -0.1670

Data Index: 5199390 (Open Web Text)

Max Activating Token Index: 214

Text #16

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8210. Min Act: -0.1699

Data Index: 6795594 (Open Web Text)

Max Activating Token Index: 473

Text #17

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8162. Min Act: -0.1700

Data Index: 1591419 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8088. Min Act: -0.1700

Data Index: 62242 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8253. Min Act: -0.1700

Data Index: 192116 (Open Web Text)

Max Activating Token Index: 716