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

Dataset: Open Web Text

Neuron 1733 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: 4.8118. Min Range: -4.8118

Max Act: 4.7858. Min Act: -0.1700

Data Index: 8037470 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7753. Min Act: -0.1700

Data Index: 515876 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.8034. Min Act: -0.1700

Data Index: 2257764 (Open Web Text)

Max Activating Token Index: 787

Text #3

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.8016. Min Act: -0.1700

Data Index: 6623286 (Open Web Text)

Max Activating Token Index: 189

Text #4

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.8118. Min Act: -0.1700

Data Index: 3939070 (Open Web Text)

Max Activating Token Index: 908

Text #5

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7818. Min Act: -0.1700

Data Index: 701912 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7561. Min Act: -0.1700

Data Index: 7162616 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7743. Min Act: -0.1700

Data Index: 7818633 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7690. Min Act: -0.1700

Data Index: 2286796 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7743. Min Act: -0.1700

Data Index: 1648414 (Open Web Text)

Max Activating Token Index: 143

Text #10

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7563. Min Act: -0.1700

Data Index: 5450543 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7777. Min Act: -0.1700

Data Index: 8768840 (Open Web Text)

Max Activating Token Index: 953

Text #12

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7786. Min Act: -0.1700

Data Index: 8650006 (Open Web Text)

Max Activating Token Index: 676

Text #13

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7617. Min Act: -0.1700

Data Index: 3426496 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7289. Min Act: -0.1700

Data Index: 8415038 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7240. Min Act: -0.1700

Data Index: 5284259 (Open Web Text)

Max Activating Token Index: 260

Text #16

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7338. Min Act: -0.1700

Data Index: 1516895 (Open Web Text)

Max Activating Token Index: 714

Text #17

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7388. Min Act: -0.1700

Data Index: 1059468 (Open Web Text)

Max Activating Token Index: 584

Text #18

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7347. Min Act: -0.1700

Data Index: 357707 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 4.8118. Min Range: -4.8118

Max Act: 4.7269. Min Act: -0.1700

Data Index: 6929139 (Open Web Text)

Max Activating Token Index: 12