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

Dataset: Open Web Text

Neuron 652 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: 5.7725. Min Range: -5.7725

Max Act: 5.7725. Min Act: -0.1700

Data Index: 5591005 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6561. Min Act: -0.1700

Data Index: 3935205 (Open Web Text)

Max Activating Token Index: 808

Text #2

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6916. Min Act: -0.1700

Data Index: 537960 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6766. Min Act: -0.1700

Data Index: 1413213 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6626. Min Act: -0.1700

Data Index: 8460054 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6795. Min Act: -0.1700

Data Index: 4838918 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6535. Min Act: -0.1700

Data Index: 5439945 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6344. Min Act: -0.1700

Data Index: 5735066 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6400. Min Act: -0.1700

Data Index: 8766211 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6304. Min Act: -0.1700

Data Index: 7791661 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6266. Min Act: -0.1700

Data Index: 3213107 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6206. Min Act: -0.1700

Data Index: 7254078 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6070. Min Act: -0.1700

Data Index: 5563416 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.6103. Min Act: -0.1700

Data Index: 1687581 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5981. Min Act: -0.1700

Data Index: 6905801 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5743. Min Act: -0.1700

Data Index: 5137102 (Open Web Text)

Max Activating Token Index: 720

Text #16

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5616. Min Act: -0.1700

Data Index: 2116901 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5780. Min Act: -0.1700

Data Index: 7135731 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5681. Min Act: -0.1700

Data Index: 6520180 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.7725. Min Range: -5.7725

Max Act: 5.5213. Min Act: -0.1700

Data Index: 2930653 (Open Web Text)

Max Activating Token Index: 4