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

Dataset: Open Web Text

Neuron 2804 in Layer 3

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: 4.9866. Min Range: -4.9866

Max Act: 4.9866. Min Act: -0.1700

Data Index: 8141180 (Open Web Text)

Max Activating Token Index: 725

Text #1

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.8837. Min Act: -0.1700

Data Index: 1609299 (Open Web Text)

Max Activating Token Index: 585

Text #2

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.8326. Min Act: -0.1700

Data Index: 4276011 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.8244. Min Act: -0.1700

Data Index: 5714752 (Open Web Text)

Max Activating Token Index: 617

Text #4

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.8124. Min Act: -0.1700

Data Index: 3923555 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.8184. Min Act: -0.1700

Data Index: 2231815 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.7752. Min Act: -0.1700

Data Index: 2274323 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.7524. Min Act: -0.1700

Data Index: 4253340 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.7410. Min Act: -0.1700

Data Index: 2370083 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6674. Min Act: -0.1700

Data Index: 637593 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6663. Min Act: -0.1700

Data Index: 894009 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6501. Min Act: -0.1700

Data Index: 1993906 (Open Web Text)

Max Activating Token Index: 811

Text #12

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6795. Min Act: -0.1700

Data Index: 6717781 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.7213. Min Act: -0.1700

Data Index: 2529690 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6801. Min Act: -0.1700

Data Index: 2689108 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6435. Min Act: -0.1700

Data Index: 1700442 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6107. Min Act: -0.1700

Data Index: 2705813 (Open Web Text)

Max Activating Token Index: 553

Text #17

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6428. Min Act: -0.1700

Data Index: 7245196 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6239. Min Act: -0.1700

Data Index: 470346 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 4.9866. Min Range: -4.9866

Max Act: 4.6378. Min Act: -0.1700

Data Index: 7870408 (Open Web Text)

Max Activating Token Index: 894