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

Dataset: Open Web Text

Neuron 435 in Layer 0

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: 3.6461. Min Range: -3.6461

Max Act: 3.6461. Min Act: -0.1700

Data Index: 2976504 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.6368. Min Act: -0.1700

Data Index: 7836782 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.6069. Min Act: -0.1700

Data Index: 1784000 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.6073. Min Act: -0.1700

Data Index: 7969439 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5811. Min Act: -0.1700

Data Index: 7141962 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5770. Min Act: -0.1700

Data Index: 6640362 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5811. Min Act: -0.1700

Data Index: 3452625 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5620. Min Act: -0.1700

Data Index: 2721206 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5808. Min Act: -0.1700

Data Index: 8257622 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5811. Min Act: -0.1700

Data Index: 3162440 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5743. Min Act: -0.1700

Data Index: 7924596 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5811. Min Act: -0.1700

Data Index: 7688434 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5317. Min Act: -0.1700

Data Index: 1331718 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5370. Min Act: -0.1700

Data Index: 6235763 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5360. Min Act: -0.1700

Data Index: 6612560 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5503. Min Act: -0.1700

Data Index: 6648385 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5355. Min Act: -0.1700

Data Index: 1548528 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5150. Min Act: -0.1700

Data Index: 5376941 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.5098. Min Act: -0.1700

Data Index: 5578239 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.6461. Min Range: -3.6461

Max Act: 3.4999. Min Act: -0.1700

Data Index: 6785424 (Open Web Text)

Max Activating Token Index: 2