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

Dataset: Open Web Text

Neuron 1970 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: 2.5008. Min Range: -2.5008

Max Act: 2.5008. Min Act: -0.1700

Data Index: 2382057 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2216. Min Act: -0.1700

Data Index: 336244 (Open Web Text)

Max Activating Token Index: 833

Text #2

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2485. Min Act: -0.1700

Data Index: 8411716 (Open Web Text)

Max Activating Token Index: 400

Text #3

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2444. Min Act: -0.1700

Data Index: 5525467 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2349. Min Act: -0.1700

Data Index: 1129553 (Open Web Text)

Max Activating Token Index: 358

Text #5

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2279. Min Act: -0.1700

Data Index: 987588 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1829. Min Act: -0.1700

Data Index: 4938473 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.2041. Min Act: -0.1700

Data Index: 6381328 (Open Web Text)

Max Activating Token Index: 916

Text #8

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1978. Min Act: -0.1700

Data Index: 7820162 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1929. Min Act: -0.1700

Data Index: 8595421 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1671. Min Act: -0.1700

Data Index: 4805714 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1709. Min Act: -0.1700

Data Index: 1517293 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1779. Min Act: -0.1700

Data Index: 2502998 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1469. Min Act: -0.1700

Data Index: 44635 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1364. Min Act: -0.1700

Data Index: 8336182 (Open Web Text)

Max Activating Token Index: 468

Text #15

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1373. Min Act: -0.1700

Data Index: 7775658 (Open Web Text)

Max Activating Token Index: 73

Text #16

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1375. Min Act: -0.1700

Data Index: 5099788 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1963. Min Act: -0.1700

Data Index: 4761708 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1670. Min Act: -0.1700

Data Index: 4702408 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 2.5008. Min Range: -2.5008

Max Act: 2.1514. Min Act: -0.1700

Data Index: 4822475 (Open Web Text)

Max Activating Token Index: 888