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

Dataset: Open Web Text

Neuron 191 in Layer 3

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: 3.6955. Min Range: -3.6955

Max Act: 3.6955. Min Act: -0.1700

Data Index: 8785299 (Open Web Text)

Max Activating Token Index: 688

Text #1

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5446. Min Act: -0.1700

Data Index: 6499794 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5792. Min Act: -0.1700

Data Index: 840265 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5831. Min Act: -0.1700

Data Index: 510502 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5591. Min Act: -0.1700

Data Index: 6695573 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5584. Min Act: -0.1700

Data Index: 6157213 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5343. Min Act: -0.1700

Data Index: 3674291 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5860. Min Act: -0.1700

Data Index: 3118456 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5850. Min Act: -0.1700

Data Index: 5505594 (Open Web Text)

Max Activating Token Index: 965

Text #9

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5635. Min Act: -0.1700

Data Index: 5936591 (Open Web Text)

Max Activating Token Index: 709

Text #10

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5734. Min Act: -0.1700

Data Index: 3170700 (Open Web Text)

Max Activating Token Index: 850

Text #11

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5488. Min Act: -0.1700

Data Index: 5562703 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5519. Min Act: -0.1700

Data Index: 7390465 (Open Web Text)

Max Activating Token Index: 274

Text #13

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5550. Min Act: -0.1700

Data Index: 6060140 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5199. Min Act: -0.1700

Data Index: 6153385 (Open Web Text)

Max Activating Token Index: 380

Text #15

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5018. Min Act: -0.1700

Data Index: 3663833 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5008. Min Act: -0.1700

Data Index: 775878 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5065. Min Act: -0.1700

Data Index: 945730 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5061. Min Act: -0.1700

Data Index: 3259924 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5095. Min Act: -0.1700

Data Index: 3138444 (Open Web Text)

Max Activating Token Index: 405