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

Dataset: Open Web Text

Neuron 568 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: 4.8841. Min Range: -4.8841

Max Act: 4.8841. Min Act: -0.1700

Data Index: 351224 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.7495. Min Act: -0.1700

Data Index: 5978156 (Open Web Text)

Max Activating Token Index: 952

Text #2

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.7469. Min Act: -0.1700

Data Index: 2841657 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.7004. Min Act: -0.1700

Data Index: 970559 (Open Web Text)

Max Activating Token Index: 701

Text #4

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.6244. Min Act: -0.1700

Data Index: 7093670 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5633. Min Act: -0.1700

Data Index: 5128423 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5889. Min Act: -0.1700

Data Index: 5877399 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5336. Min Act: -0.1700

Data Index: 7161147 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5074. Min Act: -0.1700

Data Index: 311532 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5597. Min Act: -0.1700

Data Index: 7214684 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4977. Min Act: -0.1700

Data Index: 8043849 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5280. Min Act: -0.1700

Data Index: 4489817 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4817. Min Act: -0.1700

Data Index: 6393980 (Open Web Text)

Max Activating Token Index: 414

Text #13

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4904. Min Act: -0.1700

Data Index: 1360505 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4755. Min Act: -0.1700

Data Index: 2510589 (Open Web Text)

Max Activating Token Index: 398

Text #15

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4447. Min Act: -0.1700

Data Index: 6504017 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4916. Min Act: -0.1700

Data Index: 8340704 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4792. Min Act: -0.1700

Data Index: 5252986 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.5024. Min Act: -0.1700

Data Index: 5876209 (Open Web Text)

Max Activating Token Index: 789

Text #19

Max Range: 4.8841. Min Range: -4.8841

Max Act: 4.4708. Min Act: -0.1700

Data Index: 6535346 (Open Web Text)

Max Activating Token Index: 659