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

Dataset: Open Web Text

Neuron 320 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: 4.6565. Min Range: -4.6565

Max Act: 4.6565. Min Act: -0.1700

Data Index: 2296840 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6233. Min Act: -0.1700

Data Index: 2133916 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6334. Min Act: -0.1700

Data Index: 345299 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6373. Min Act: -0.1700

Data Index: 4924318 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6236. Min Act: -0.1700

Data Index: 8796247 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6095. Min Act: -0.1700

Data Index: 3604017 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6209. Min Act: -0.1700

Data Index: 7853333 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6175. Min Act: -0.1700

Data Index: 698674 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.6207. Min Act: -0.1700

Data Index: 7352526 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5843. Min Act: -0.1700

Data Index: 7166018 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5707. Min Act: -0.1700

Data Index: 8109298 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5832. Min Act: -0.1700

Data Index: 7973111 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5653. Min Act: -0.1700

Data Index: 2590774 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5637. Min Act: -0.1700

Data Index: 4938046 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5756. Min Act: -0.1700

Data Index: 4880250 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5837. Min Act: -0.1700

Data Index: 4846145 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5734. Min Act: -0.1700

Data Index: 3929097 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5779. Min Act: -0.1700

Data Index: 3813561 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5620. Min Act: -0.1700

Data Index: 3549395 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.6565. Min Range: -4.6565

Max Act: 4.5684. Min Act: -0.1700

Data Index: 2886156 (Open Web Text)

Max Activating Token Index: 6