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

Dataset: Open Web Text

Neuron 1041 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: 3.9899. Min Range: -3.9899

Max Act: 3.9899. Min Act: -0.1700

Data Index: 2917024 (Open Web Text)

Max Activating Token Index: 711

Text #1

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9409. Min Act: -0.1700

Data Index: 644038 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9451. Min Act: -0.1700

Data Index: 77516 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9311. Min Act: -0.1700

Data Index: 379382 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9191. Min Act: -0.1700

Data Index: 7677009 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9444. Min Act: -0.1700

Data Index: 7907364 (Open Web Text)

Max Activating Token Index: 375

Text #6

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8811. Min Act: -0.1700

Data Index: 1884875 (Open Web Text)

Max Activating Token Index: 921

Text #7

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9032. Min Act: -0.1700

Data Index: 1334502 (Open Web Text)

Max Activating Token Index: 377

Text #8

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9295. Min Act: -0.1700

Data Index: 6007282 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.9059. Min Act: -0.1700

Data Index: 7370780 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8893. Min Act: -0.1700

Data Index: 1273845 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8673. Min Act: -0.1700

Data Index: 6681843 (Open Web Text)

Max Activating Token Index: 750

Text #12

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8354. Min Act: -0.1700

Data Index: 3542029 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8496. Min Act: -0.1700

Data Index: 814318 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8529. Min Act: -0.1700

Data Index: 3092118 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8071. Min Act: -0.1700

Data Index: 8563902 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.7943. Min Act: -0.1700

Data Index: 3211707 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8176. Min Act: -0.1700

Data Index: 2588788 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.8048. Min Act: -0.1700

Data Index: 5386163 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 3.9899. Min Range: -3.9899

Max Act: 3.7695. Min Act: -0.1700

Data Index: 6351380 (Open Web Text)

Max Activating Token Index: 612