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

Dataset: Open Web Text

Neuron 486 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: 5.4882. Min Range: -5.4882

Max Act: 5.4882. Min Act: -0.1700

Data Index: 5152698 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.4651. Min Act: -0.1700

Data Index: 8465668 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.4504. Min Act: -0.1700

Data Index: 1826011 (Open Web Text)

Max Activating Token Index: 585

Text #3

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3703. Min Act: -0.1700

Data Index: 2160465 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3939. Min Act: -0.1700

Data Index: 3150065 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3561. Min Act: -0.1700

Data Index: 4172944 (Open Web Text)

Max Activating Token Index: 925

Text #6

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3693. Min Act: -0.1700

Data Index: 5139303 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3440. Min Act: -0.1700

Data Index: 7104786 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3543. Min Act: -0.1700

Data Index: 926250 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3243. Min Act: -0.1700

Data Index: 4026751 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3271. Min Act: -0.1700

Data Index: 3082932 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2864. Min Act: -0.1700

Data Index: 598113 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3227. Min Act: -0.1700

Data Index: 6603352 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3915. Min Act: -0.1700

Data Index: 2255947 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3055. Min Act: -0.1700

Data Index: 6340755 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2726. Min Act: -0.1700

Data Index: 3590212 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2767. Min Act: -0.1700

Data Index: 961182 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2571. Min Act: -0.1700

Data Index: 5014148 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.2898. Min Act: -0.1700

Data Index: 5135048 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.4882. Min Range: -5.4882

Max Act: 5.3191. Min Act: -0.1700

Data Index: 2528313 (Open Web Text)

Max Activating Token Index: 628