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

Dataset: Open Web Text

Neuron 1318 in Layer 0

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: 4.0476. Min Range: -4.0476

Max Act: 4.0476. Min Act: -0.1700

Data Index: 458406 (Open Web Text)

Max Activating Token Index: 92

Text #1

Max Range: 4.0476. Min Range: -4.0476

Max Act: 4.0296. Min Act: -0.1700

Data Index: 3633264 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.0476. Min Range: -4.0476

Max Act: 4.0464. Min Act: -0.1700

Data Index: 4513325 (Open Web Text)

Max Activating Token Index: 989

Text #3

Max Range: 4.0476. Min Range: -4.0476

Max Act: 4.0193. Min Act: -0.1700

Data Index: 8302275 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9829. Min Act: -0.1700

Data Index: 5858225 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9648. Min Act: -0.1700

Data Index: 6634641 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9769. Min Act: -0.1700

Data Index: 441422 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9626. Min Act: -0.1700

Data Index: 5544569 (Open Web Text)

Max Activating Token Index: 928

Text #8

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9374. Min Act: -0.1700

Data Index: 1714242 (Open Web Text)

Max Activating Token Index: 927

Text #9

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9389. Min Act: -0.1700

Data Index: 2239666 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9502. Min Act: -0.1700

Data Index: 1261393 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9289. Min Act: -0.1700

Data Index: 814154 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9374. Min Act: -0.1700

Data Index: 7891550 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9230. Min Act: -0.1700

Data Index: 5875567 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9252. Min Act: -0.1700

Data Index: 3578179 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.8882. Min Act: -0.1700

Data Index: 4655801 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9261. Min Act: -0.1700

Data Index: 3155524 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.8924. Min Act: -0.1700

Data Index: 5321638 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9065. Min Act: -0.1700

Data Index: 5347168 (Open Web Text)

Max Activating Token Index: 831

Text #19

Max Range: 4.0476. Min Range: -4.0476

Max Act: 3.9183. Min Act: -0.1700

Data Index: 5409744 (Open Web Text)

Max Activating Token Index: 726