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

Dataset: Open Web Text

Neuron 1994 in Layer 1

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: 4.0125. Min Range: -4.0125

Max Act: 4.0125. Min Act: -0.1700

Data Index: 5606560 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 4.0125. Min Range: -4.0125

Max Act: 4.0037. Min Act: -0.1700

Data Index: 878588 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9375. Min Act: -0.1700

Data Index: 2978881 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9319. Min Act: -0.1700

Data Index: 5899179 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9523. Min Act: -0.1700

Data Index: 4345436 (Open Web Text)

Max Activating Token Index: 591

Text #5

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9694. Min Act: -0.1700

Data Index: 1530317 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9544. Min Act: -0.1700

Data Index: 8089721 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9002. Min Act: -0.1700

Data Index: 8801170 (Open Web Text)

Max Activating Token Index: 565

Text #8

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8880. Min Act: -0.1700

Data Index: 531608 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8849. Min Act: -0.1700

Data Index: 8170037 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9008. Min Act: -0.1700

Data Index: 3453716 (Open Web Text)

Max Activating Token Index: 876

Text #11

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8734. Min Act: -0.1700

Data Index: 3271197 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8888. Min Act: -0.1700

Data Index: 4828508 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8475. Min Act: -0.1700

Data Index: 3357306 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8702. Min Act: -0.1700

Data Index: 7157660 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8636. Min Act: -0.1700

Data Index: 3506288 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8693. Min Act: -0.1700

Data Index: 6551983 (Open Web Text)

Max Activating Token Index: 417

Text #17

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8727. Min Act: -0.1700

Data Index: 5200178 (Open Web Text)

Max Activating Token Index: 245

Text #18

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8639. Min Act: -0.1700

Data Index: 4467905 (Open Web Text)

Max Activating Token Index: 581

Text #19

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.8551. Min Act: -0.1700

Data Index: 8208621 (Open Web Text)

Max Activating Token Index: 5