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

Dataset: Open Web Text

Neuron 2607 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: 4.8625. Min Range: -4.8625

Max Act: 4.8625. Min Act: -0.1700

Data Index: 2710158 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.8001. Min Act: -0.1700

Data Index: 4249917 (Open Web Text)

Max Activating Token Index: 805

Text #2

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.7791. Min Act: -0.1700

Data Index: 836537 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.7203. Min Act: -0.1700

Data Index: 6889255 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.6886. Min Act: -0.1700

Data Index: 7200162 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.6824. Min Act: -0.1700

Data Index: 2132785 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.6620. Min Act: -0.1700

Data Index: 6786860 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.6391. Min Act: -0.1700

Data Index: 641979 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.6166. Min Act: -0.1700

Data Index: 1157682 (Open Web Text)

Max Activating Token Index: 332

Text #9

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5752. Min Act: -0.1700

Data Index: 5867577 (Open Web Text)

Max Activating Token Index: 257

Text #10

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5472. Min Act: -0.1700

Data Index: 618473 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5120. Min Act: -0.1700

Data Index: 8766068 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5117. Min Act: -0.1700

Data Index: 1920225 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.4705. Min Act: -0.1700

Data Index: 5631853 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5025. Min Act: -0.1700

Data Index: 4861615 (Open Web Text)

Max Activating Token Index: 687

Text #15

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.5018. Min Act: -0.1700

Data Index: 7775930 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.4987. Min Act: -0.1700

Data Index: 744513 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.4961. Min Act: -0.1700

Data Index: 2417111 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.4932. Min Act: -0.1700

Data Index: 6925816 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 4.8625. Min Range: -4.8625

Max Act: 4.4367. Min Act: -0.1700

Data Index: 7690545 (Open Web Text)

Max Activating Token Index: 1012