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

Dataset: Open Web Text

Neuron 1638 in Layer 3

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: 4.2721. Min Range: -4.2721

Max Act: 4.2721. Min Act: -0.1700

Data Index: 7908365 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0920. Min Act: -0.1700

Data Index: 7908367 (Open Web Text)

Max Activating Token Index: 889

Text #2

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0920. Min Act: -0.1700

Data Index: 5942689 (Open Web Text)

Max Activating Token Index: 787

Text #3

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0671. Min Act: -0.1700

Data Index: 144723 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.2721. Min Range: -4.2721

Max Act: 4.0369. Min Act: -0.1700

Data Index: 110928 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9933. Min Act: -0.1700

Data Index: 6096367 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9581. Min Act: -0.1700

Data Index: 531688 (Open Web Text)

Max Activating Token Index: 232

Text #7

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9559. Min Act: -0.1700

Data Index: 144731 (Open Web Text)

Max Activating Token Index: 227

Text #8

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9549. Min Act: -0.1700

Data Index: 1578295 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9249. Min Act: -0.1700

Data Index: 7908372 (Open Web Text)

Max Activating Token Index: 549

Text #10

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9234. Min Act: -0.1700

Data Index: 6725888 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9299. Min Act: -0.1700

Data Index: 7785236 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.9030. Min Act: -0.1700

Data Index: 3752635 (Open Web Text)

Max Activating Token Index: 388

Text #13

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8516. Min Act: -0.1700

Data Index: 3179384 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8406. Min Act: -0.1700

Data Index: 7987522 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8675. Min Act: -0.1700

Data Index: 6864602 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8440. Min Act: -0.1700

Data Index: 10793 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8151. Min Act: -0.1700

Data Index: 8202555 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8787. Min Act: -0.1700

Data Index: 7798663 (Open Web Text)

Max Activating Token Index: 347

Text #19

Max Range: 4.2721. Min Range: -4.2721

Max Act: 3.8194. Min Act: -0.1700

Data Index: 1947682 (Open Web Text)

Max Activating Token Index: 364