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

Dataset: Open Web Text

Neuron 1276 in Layer 1

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: 1.5710. Min Range: -1.5710

Max Act: 1.5710. Min Act: -0.1700

Data Index: 71690 (Open Web Text)

Max Activating Token Index: 961

Text #1

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.5334. Min Act: -0.1700

Data Index: 5024052 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4971. Min Act: -0.1700

Data Index: 7062295 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.5038. Min Act: -0.1700

Data Index: 3259519 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4912. Min Act: -0.1700

Data Index: 2105486 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4991. Min Act: -0.1700

Data Index: 6500012 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4858. Min Act: -0.1700

Data Index: 8422230 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4837. Min Act: -0.1700

Data Index: 9680 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4831. Min Act: -0.1700

Data Index: 4969074 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4685. Min Act: -0.1700

Data Index: 7217194 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4703. Min Act: -0.1700

Data Index: 5820839 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4578. Min Act: -0.1700

Data Index: 3755093 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4609. Min Act: -0.1700

Data Index: 665266 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4630. Min Act: -0.1700

Data Index: 3036951 (Open Web Text)

Max Activating Token Index: 124

Text #14

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4583. Min Act: -0.1700

Data Index: 8754636 (Open Web Text)

Max Activating Token Index: 979

Text #15

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4685. Min Act: -0.1700

Data Index: 5781475 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4678. Min Act: -0.1700

Data Index: 7456689 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4426. Min Act: -0.1700

Data Index: 3357356 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4675. Min Act: -0.1700

Data Index: 5381097 (Open Web Text)

Max Activating Token Index: 948

Text #19

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4542. Min Act: -0.1700

Data Index: 1407532 (Open Web Text)

Max Activating Token Index: 889