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

Dataset: Open Web Text

Neuron 2268 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: 4.8162. Min Range: -4.8162

Max Act: 4.7779. Min Act: -0.1700

Data Index: 145419 (Open Web Text)

Max Activating Token Index: 853

Text #1

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.8065. Min Act: -0.1700

Data Index: 1563236 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7841. Min Act: -0.1700

Data Index: 4829240 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.8162. Min Act: -0.1700

Data Index: 8620279 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7766. Min Act: -0.1700

Data Index: 5059779 (Open Web Text)

Max Activating Token Index: 107

Text #5

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7532. Min Act: -0.1700

Data Index: 2207832 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7149. Min Act: -0.1700

Data Index: 4381619 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7547. Min Act: -0.1700

Data Index: 4593675 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7347. Min Act: -0.1700

Data Index: 4121397 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7030. Min Act: -0.1700

Data Index: 3916259 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7028. Min Act: -0.1700

Data Index: 4493440 (Open Web Text)

Max Activating Token Index: 181

Text #11

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7084. Min Act: -0.1700

Data Index: 5071102 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7071. Min Act: -0.1700

Data Index: 3727160 (Open Web Text)

Max Activating Token Index: 576

Text #13

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7006. Min Act: -0.1700

Data Index: 8132635 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6723. Min Act: -0.1700

Data Index: 1426841 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.7138. Min Act: -0.1700

Data Index: 6883163 (Open Web Text)

Max Activating Token Index: 209

Text #16

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6623. Min Act: -0.1700

Data Index: 3091218 (Open Web Text)

Max Activating Token Index: 849

Text #17

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6724. Min Act: -0.1700

Data Index: 5967215 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6768. Min Act: -0.1700

Data Index: 6505730 (Open Web Text)

Max Activating Token Index: 496

Text #19

Max Range: 4.8162. Min Range: -4.8162

Max Act: 4.6899. Min Act: -0.1700

Data Index: 6650047 (Open Web Text)

Max Activating Token Index: 1017