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

Dataset: Open Web Text

Neuron 290 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: 4.5092. Min Range: -4.5092

Max Act: 4.5092. Min Act: -0.1700

Data Index: 7880448 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 4.5092. Min Range: -4.5092

Max Act: 4.4203. Min Act: -0.1700

Data Index: 1324886 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 4.5092. Min Range: -4.5092

Max Act: 4.0343. Min Act: -0.1700

Data Index: 2951139 (Open Web Text)

Max Activating Token Index: 787

Text #3

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.8618. Min Act: -0.1700

Data Index: 6475189 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.6534. Min Act: -0.1700

Data Index: 6319095 (Open Web Text)

Max Activating Token Index: 36

Text #5

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.5802. Min Act: -0.1700

Data Index: 8346266 (Open Web Text)

Max Activating Token Index: 815

Text #6

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.5496. Min Act: -0.1700

Data Index: 5827292 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.6311. Min Act: -0.1700

Data Index: 2315309 (Open Web Text)

Max Activating Token Index: 280

Text #8

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.5857. Min Act: -0.1700

Data Index: 4487374 (Open Web Text)

Max Activating Token Index: 546

Text #9

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.5365. Min Act: -0.1700

Data Index: 1280175 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.5368. Min Act: -0.1700

Data Index: 4984989 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.4731. Min Act: -0.1700

Data Index: 7708484 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.4401. Min Act: -0.1683

Data Index: 7743962 (Open Web Text)

Max Activating Token Index: 943

Text #13

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.4410. Min Act: -0.1700

Data Index: 3974145 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.3887. Min Act: -0.1700

Data Index: 1964628 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.3669. Min Act: -0.1700

Data Index: 2812891 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.4031. Min Act: -0.1700

Data Index: 6269616 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.3483. Min Act: -0.1700

Data Index: 5844644 (Open Web Text)

Max Activating Token Index: 704

Text #18

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.3739. Min Act: -0.1700

Data Index: 8321880 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 4.5092. Min Range: -4.5092

Max Act: 3.3337. Min Act: -0.1700

Data Index: 2563909 (Open Web Text)

Max Activating Token Index: 19