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

Dataset: Open Web Text

Neuron 906 in Layer 5

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: 4.5851. Min Range: -4.5851

Max Act: 4.5714. Min Act: -0.1700

Data Index: 8353763 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5851. Min Act: -0.1700

Data Index: 789331 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5149. Min Act: -0.1700

Data Index: 7619105 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5113. Min Act: -0.1700

Data Index: 137744 (Open Web Text)

Max Activating Token Index: 886

Text #4

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5161. Min Act: -0.1700

Data Index: 3730061 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5213. Min Act: -0.1700

Data Index: 7128527 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5083. Min Act: -0.1700

Data Index: 8097277 (Open Web Text)

Max Activating Token Index: 433

Text #7

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4609. Min Act: -0.1700

Data Index: 8775958 (Open Web Text)

Max Activating Token Index: 848

Text #8

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4516. Min Act: -0.1700

Data Index: 7949231 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4561. Min Act: -0.1700

Data Index: 1312463 (Open Web Text)

Max Activating Token Index: 491

Text #10

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4761. Min Act: -0.1700

Data Index: 7180682 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4314. Min Act: -0.1700

Data Index: 169676 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4180. Min Act: -0.1700

Data Index: 6298283 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4155. Min Act: -0.1700

Data Index: 2972792 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4722. Min Act: -0.1700

Data Index: 3264301 (Open Web Text)

Max Activating Token Index: 380

Text #15

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3876. Min Act: -0.1700

Data Index: 7491378 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4160. Min Act: -0.1700

Data Index: 3629708 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3921. Min Act: -0.1700

Data Index: 349850 (Open Web Text)

Max Activating Token Index: 953

Text #18

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4207. Min Act: -0.1700

Data Index: 1400901 (Open Web Text)

Max Activating Token Index: 899

Text #19

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4290. Min Act: -0.1700

Data Index: 8384758 (Open Web Text)

Max Activating Token Index: 84