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

Dataset: Open Web Text

Neuron 2806 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: 3.2974. Min Range: -3.2974

Max Act: 3.2974. Min Act: -0.1700

Data Index: 6871190 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2852. Min Act: -0.1700

Data Index: 7475499 (Open Web Text)

Max Activating Token Index: 31

Text #2

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2798. Min Act: -0.1700

Data Index: 3913954 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1960. Min Act: -0.1700

Data Index: 4497810 (Open Web Text)

Max Activating Token Index: 698

Text #4

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1885. Min Act: -0.1700

Data Index: 6637752 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1796. Min Act: -0.1700

Data Index: 1128422 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1475. Min Act: -0.1700

Data Index: 7650775 (Open Web Text)

Max Activating Token Index: 350

Text #7

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1303. Min Act: -0.1700

Data Index: 2057402 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1297. Min Act: -0.1700

Data Index: 5428565 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1289. Min Act: -0.1700

Data Index: 3483071 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1110. Min Act: -0.1700

Data Index: 217935 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1299. Min Act: -0.1700

Data Index: 4298716 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1094. Min Act: -0.1700

Data Index: 5608947 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1059. Min Act: -0.1700

Data Index: 5858924 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.0948. Min Act: -0.1700

Data Index: 8332276 (Open Web Text)

Max Activating Token Index: 320

Text #15

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1013. Min Act: -0.1700

Data Index: 4055302 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1019. Min Act: -0.1700

Data Index: 4015832 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.0863. Min Act: -0.1700

Data Index: 4237236 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1827529 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.0886. Min Act: -0.1700

Data Index: 6300869 (Open Web Text)

Max Activating Token Index: 552