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

Dataset: Open Web Text

Neuron 1659 in Layer 5

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: 4.2804. Min Range: -4.2804

Max Act: 4.2804. Min Act: -0.1700

Data Index: 7799396 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.1668. Min Act: -0.1700

Data Index: 413814 (Open Web Text)

Max Activating Token Index: 848

Text #2

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.1422. Min Act: -0.1700

Data Index: 2823776 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.0953. Min Act: -0.1700

Data Index: 2847725 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.0763. Min Act: -0.1700

Data Index: 1915457 (Open Web Text)

Max Activating Token Index: 359

Text #5

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.1041. Min Act: -0.1700

Data Index: 7799395 (Open Web Text)

Max Activating Token Index: 839

Text #6

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.0535. Min Act: -0.1700

Data Index: 3384774 (Open Web Text)

Max Activating Token Index: 344

Text #7

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.0325. Min Act: -0.1700

Data Index: 4542140 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 4.2804. Min Range: -4.2804

Max Act: 4.0191. Min Act: -0.1700

Data Index: 408039 (Open Web Text)

Max Activating Token Index: 989

Text #9

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9933. Min Act: -0.1700

Data Index: 973330 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9326. Min Act: -0.1700

Data Index: 2739366 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9941. Min Act: -0.1700

Data Index: 3946353 (Open Web Text)

Max Activating Token Index: 510

Text #12

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9554. Min Act: -0.1700

Data Index: 3602543 (Open Web Text)

Max Activating Token Index: 676

Text #13

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9627. Min Act: -0.1700

Data Index: 8301594 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9523. Min Act: -0.1700

Data Index: 5116721 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.8980. Min Act: -0.1700

Data Index: 3244718 (Open Web Text)

Max Activating Token Index: 206

Text #16

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9023. Min Act: -0.1700

Data Index: 7790802 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.8993. Min Act: -0.1700

Data Index: 5076782 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.9196. Min Act: -0.1700

Data Index: 4070716 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 4.2804. Min Range: -4.2804

Max Act: 3.8961. Min Act: -0.1700

Data Index: 3384773 (Open Web Text)

Max Activating Token Index: 280