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

Dataset: Open Web Text

Neuron 657 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: 3.7920. Min Range: -3.7920

Max Act: 3.7920. Min Act: -0.1700

Data Index: 4284757 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.7854. Min Act: -0.1700

Data Index: 6809874 (Open Web Text)

Max Activating Token Index: 776

Text #2

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.7181. Min Act: -0.1700

Data Index: 6727426 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6825. Min Act: -0.1700

Data Index: 888848 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6577. Min Act: -0.1700

Data Index: 277990 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6270. Min Act: -0.1700

Data Index: 7754278 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6225. Min Act: -0.1700

Data Index: 8000625 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6237. Min Act: -0.1700

Data Index: 1366819 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6329. Min Act: -0.1700

Data Index: 4179283 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5879. Min Act: -0.1700

Data Index: 6809886 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5927. Min Act: -0.1700

Data Index: 8580817 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5776. Min Act: -0.1700

Data Index: 8539843 (Open Web Text)

Max Activating Token Index: 252

Text #12

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6008. Min Act: -0.1700

Data Index: 3217200 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6219. Min Act: -0.1700

Data Index: 8161397 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5934. Min Act: -0.1700

Data Index: 7430926 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5740. Min Act: -0.1700

Data Index: 7565094 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5758. Min Act: -0.1700

Data Index: 3783786 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.6030. Min Act: -0.1700

Data Index: 4734965 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5690. Min Act: -0.1700

Data Index: 6974493 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 3.7920. Min Range: -3.7920

Max Act: 3.5268. Min Act: -0.1700

Data Index: 7668984 (Open Web Text)

Max Activating Token Index: 483