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

Dataset: Open Web Text

Neuron 1285 in Layer 2

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: 1.8029. Min Range: -1.8029

Max Act: 1.7995. Min Act: -0.1700

Data Index: 2276500 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.8009. Min Act: -0.1607

Data Index: 78573 (Open Web Text)

Max Activating Token Index: 944

Text #2

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7956. Min Act: -0.1700

Data Index: 8695752 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.8029. Min Act: -0.1696

Data Index: 3060588 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7943. Min Act: -0.1700

Data Index: 8487821 (Open Web Text)

Max Activating Token Index: 345

Text #5

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7888. Min Act: -0.1700

Data Index: 8112184 (Open Web Text)

Max Activating Token Index: 970

Text #6

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7890. Min Act: -0.1699

Data Index: 3377588 (Open Web Text)

Max Activating Token Index: 207

Text #7

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7910. Min Act: -0.1699

Data Index: 964805 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7802. Min Act: -0.1700

Data Index: 6473257 (Open Web Text)

Max Activating Token Index: 69

Text #9

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7740. Min Act: -0.1700

Data Index: 4136608 (Open Web Text)

Max Activating Token Index: 685

Text #10

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7810. Min Act: -0.1700

Data Index: 8044028 (Open Web Text)

Max Activating Token Index: 687

Text #11

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7903. Min Act: -0.1700

Data Index: 4315931 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7750. Min Act: -0.1699

Data Index: 5195455 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7782. Min Act: -0.1700

Data Index: 2157885 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7833. Min Act: -0.1700

Data Index: 6585123 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7680. Min Act: -0.1696

Data Index: 7631649 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7755. Min Act: -0.1700

Data Index: 5898777 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7737. Min Act: -0.1700

Data Index: 3661199 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7521. Min Act: -0.1700

Data Index: 5788248 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 1.8029. Min Range: -1.8029

Max Act: 1.7603. Min Act: -0.1700

Data Index: 1034312 (Open Web Text)

Max Activating Token Index: 855