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

Dataset: Open Web Text

Neuron 2580 in Layer 4

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: 3.0987. Min Range: -3.0987

Max Act: 3.0793. Min Act: -0.1700

Data Index: 2665293 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 3.0987. Min Range: -3.0987

Max Act: 3.0987. Min Act: -0.1700

Data Index: 3439646 (Open Web Text)

Max Activating Token Index: 452

Text #2

Max Range: 3.0987. Min Range: -3.0987

Max Act: 3.0167. Min Act: -0.1700

Data Index: 2592800 (Open Web Text)

Max Activating Token Index: 871

Text #3

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.9959. Min Act: -0.1700

Data Index: 998899 (Open Web Text)

Max Activating Token Index: 543

Text #4

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.9191. Min Act: -0.1700

Data Index: 2372324 (Open Web Text)

Max Activating Token Index: 887

Text #5

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.9805. Min Act: -0.1700

Data Index: 2592797 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.9218. Min Act: -0.1700

Data Index: 4266726 (Open Web Text)

Max Activating Token Index: 854

Text #7

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8776. Min Act: -0.1700

Data Index: 1680917 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8619. Min Act: -0.1700

Data Index: 2191563 (Open Web Text)

Max Activating Token Index: 595

Text #9

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8606. Min Act: -0.1700

Data Index: 7646011 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8604. Min Act: -0.1700

Data Index: 4591764 (Open Web Text)

Max Activating Token Index: 210

Text #11

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8322. Min Act: -0.1700

Data Index: 3963892 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8073. Min Act: -0.1700

Data Index: 3351620 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8277. Min Act: -0.1700

Data Index: 7007749 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8195. Min Act: -0.1700

Data Index: 3528576 (Open Web Text)

Max Activating Token Index: 786

Text #15

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8274. Min Act: -0.1700

Data Index: 5902504 (Open Web Text)

Max Activating Token Index: 904

Text #16

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8241. Min Act: -0.1700

Data Index: 324723 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.7918. Min Act: -0.1700

Data Index: 3533783 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.7990. Min Act: -0.1700

Data Index: 3636419 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.0987. Min Range: -3.0987

Max Act: 2.8172. Min Act: -0.1700

Data Index: 2087372 (Open Web Text)

Max Activating Token Index: 223