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

Dataset: Open Web Text

Neuron 215 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: 2.5384. Min Range: -2.5384

Max Act: 2.5384. Min Act: -0.1700

Data Index: 1753610 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5212. Min Act: -0.1700

Data Index: 6448123 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5242. Min Act: -0.1700

Data Index: 4995583 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5248. Min Act: -0.1700

Data Index: 3512186 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5172. Min Act: -0.1700

Data Index: 61791 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5229. Min Act: -0.1700

Data Index: 1520941 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5019. Min Act: -0.1700

Data Index: 5588252 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.5128. Min Act: -0.1700

Data Index: 5565033 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4866. Min Act: -0.1700

Data Index: 3702939 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4941. Min Act: -0.1700

Data Index: 3007086 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4880. Min Act: -0.1700

Data Index: 283020 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4903. Min Act: -0.1700

Data Index: 1393851 (Open Web Text)

Max Activating Token Index: 569

Text #12

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4955. Min Act: -0.1700

Data Index: 8177762 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4798. Min Act: -0.1700

Data Index: 3548029 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4831. Min Act: -0.1700

Data Index: 1425817 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4797. Min Act: -0.1700

Data Index: 3843067 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4820. Min Act: -0.1700

Data Index: 3999690 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4815. Min Act: -0.1700

Data Index: 3409199 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4750. Min Act: -0.1700

Data Index: 6404645 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.5384. Min Range: -2.5384

Max Act: 2.4757. Min Act: -0.1700

Data Index: 4251638 (Open Web Text)

Max Activating Token Index: 4