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

Dataset: Open Web Text

Neuron 46 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: 3.3580. Min Range: -3.3580

Max Act: 3.3263. Min Act: -0.1700

Data Index: 4820164 (Open Web Text)

Max Activating Token Index: 779

Text #1

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3292. Min Act: -0.1700

Data Index: 1815590 (Open Web Text)

Max Activating Token Index: 87

Text #2

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3580. Min Act: -0.1700

Data Index: 3530902 (Open Web Text)

Max Activating Token Index: 449

Text #3

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3156. Min Act: -0.1700

Data Index: 5784638 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3227. Min Act: -0.1700

Data Index: 611048 (Open Web Text)

Max Activating Token Index: 423

Text #5

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2998. Min Act: -0.1700

Data Index: 3770612 (Open Web Text)

Max Activating Token Index: 370

Text #6

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2647. Min Act: -0.1700

Data Index: 7793281 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2759. Min Act: -0.1700

Data Index: 571664 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2520. Min Act: -0.1700

Data Index: 6456105 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2486. Min Act: -0.1700

Data Index: 4707792 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1136303 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2340. Min Act: -0.1700

Data Index: 423464 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2252. Min Act: -0.1700

Data Index: 5959558 (Open Web Text)

Max Activating Token Index: 791

Text #13

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2025. Min Act: -0.1700

Data Index: 8206665 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2167. Min Act: -0.1700

Data Index: 414700 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2096. Min Act: -0.1700

Data Index: 8052447 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2117. Min Act: -0.1700

Data Index: 7420426 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2070. Min Act: -0.1700

Data Index: 4762606 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.1812. Min Act: -0.1700

Data Index: 646055 (Open Web Text)

Max Activating Token Index: 982

Text #19

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.2125. Min Act: -0.1700

Data Index: 2728539 (Open Web Text)

Max Activating Token Index: 68