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

Dataset: Open Web Text

Neuron 1791 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: 4.5837. Min Range: -4.5837

Max Act: 4.5837. Min Act: -0.1700

Data Index: 4366091 (Open Web Text)

Max Activating Token Index: 737

Text #1

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.5239. Min Act: -0.1700

Data Index: 3403323 (Open Web Text)

Max Activating Token Index: 738

Text #2

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4511. Min Act: -0.1700

Data Index: 172479 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4368. Min Act: -0.1700

Data Index: 1718799 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4075. Min Act: -0.1700

Data Index: 4446422 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4325. Min Act: -0.1700

Data Index: 5067478 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4165. Min Act: -0.1700

Data Index: 4885837 (Open Web Text)

Max Activating Token Index: 320

Text #7

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3787. Min Act: -0.1700

Data Index: 4853072 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3769. Min Act: -0.1700

Data Index: 1066943 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3895. Min Act: -0.1700

Data Index: 4458609 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3802. Min Act: -0.1700

Data Index: 2799149 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3927. Min Act: -0.1700

Data Index: 1922178 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3646. Min Act: -0.1700

Data Index: 1258543 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4043. Min Act: -0.1700

Data Index: 3512180 (Open Web Text)

Max Activating Token Index: 789

Text #14

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4041. Min Act: -0.1700

Data Index: 5730149 (Open Web Text)

Max Activating Token Index: 772

Text #15

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4077. Min Act: -0.1700

Data Index: 5858353 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3947. Min Act: -0.1700

Data Index: 6809931 (Open Web Text)

Max Activating Token Index: 365

Text #17

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.3965. Min Act: -0.1700

Data Index: 717286 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4100. Min Act: -0.1700

Data Index: 8071342 (Open Web Text)

Max Activating Token Index: 311

Text #19

Max Range: 4.5837. Min Range: -4.5837

Max Act: 4.4139. Min Act: -0.1700

Data Index: 3178759 (Open Web Text)

Max Activating Token Index: 382