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

Dataset: Open Web Text

Neuron 2878 in Layer 6

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: 4.0005. Min Range: -4.0005

Max Act: 4.0005. Min Act: -0.1700

Data Index: 3644850 (Open Web Text)

Max Activating Token Index: 385

Text #1

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9456. Min Act: -0.1700

Data Index: 2306397 (Open Web Text)

Max Activating Token Index: 60

Text #2

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9381. Min Act: -0.1700

Data Index: 1909970 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9346. Min Act: -0.1700

Data Index: 2878063 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9280. Min Act: -0.1700

Data Index: 2604053 (Open Web Text)

Max Activating Token Index: 223

Text #5

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9257. Min Act: -0.1700

Data Index: 8442515 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9144. Min Act: -0.1700

Data Index: 8139793 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9158. Min Act: -0.1700

Data Index: 4692393 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8906. Min Act: -0.1700

Data Index: 8375930 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8810. Min Act: -0.1700

Data Index: 8236038 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8738. Min Act: -0.1700

Data Index: 5926544 (Open Web Text)

Max Activating Token Index: 480

Text #11

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8875. Min Act: -0.1700

Data Index: 5829977 (Open Web Text)

Max Activating Token Index: 927

Text #12

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8819. Min Act: -0.1700

Data Index: 4658852 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.9006. Min Act: -0.1700

Data Index: 335334 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8409. Min Act: -0.1700

Data Index: 5838003 (Open Web Text)

Max Activating Token Index: 200

Text #15

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8453. Min Act: -0.1700

Data Index: 1243623 (Open Web Text)

Max Activating Token Index: 205

Text #16

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8650. Min Act: -0.1700

Data Index: 2434659 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8607. Min Act: -0.1700

Data Index: 7608793 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8345. Min Act: -0.1700

Data Index: 149684 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 4.0005. Min Range: -4.0005

Max Act: 3.8505. Min Act: -0.1700

Data Index: 4547947 (Open Web Text)

Max Activating Token Index: 374