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

Dataset: Open Web Text

Neuron 2974 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: 4.8056. Min Range: -4.8056

Max Act: 4.7651. Min Act: -0.1700

Data Index: 6032812 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.8056. Min Act: -0.1700

Data Index: 7711759 (Open Web Text)

Max Activating Token Index: 873

Text #2

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.5181. Min Act: -0.1700

Data Index: 3781742 (Open Web Text)

Max Activating Token Index: 346

Text #3

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.5449. Min Act: -0.1700

Data Index: 5857903 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.5284. Min Act: -0.1700

Data Index: 1438173 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4983. Min Act: -0.1700

Data Index: 1474591 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4542. Min Act: -0.1700

Data Index: 5798361 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4403. Min Act: -0.1700

Data Index: 6880776 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4399. Min Act: -0.1700

Data Index: 7697614 (Open Web Text)

Max Activating Token Index: 627

Text #9

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4300. Min Act: -0.1700

Data Index: 5122280 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3546. Min Act: -0.1700

Data Index: 101212 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4098. Min Act: -0.1700

Data Index: 1420146 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3991. Min Act: -0.1700

Data Index: 811204 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.4038. Min Act: -0.1700

Data Index: 3733040 (Open Web Text)

Max Activating Token Index: 879

Text #14

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3717. Min Act: -0.1700

Data Index: 5864449 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3726. Min Act: -0.1700

Data Index: 8405205 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3554. Min Act: -0.1700

Data Index: 3387560 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.3272. Min Act: -0.1700

Data Index: 565956 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.2922. Min Act: -0.1700

Data Index: 4971786 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.8056. Min Range: -4.8056

Max Act: 4.2954. Min Act: -0.1700

Data Index: 3519751 (Open Web Text)

Max Activating Token Index: 184