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

Dataset: Open Web Text

Neuron 3070 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: 3.7346. Min Range: -3.7346

Max Act: 3.7346. Min Act: -0.1700

Data Index: 5710348 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.7221. Min Act: -0.1700

Data Index: 1420364 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.6092. Min Act: -0.1700

Data Index: 6045405 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.6250. Min Act: -0.1700

Data Index: 7572450 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5850. Min Act: -0.1700

Data Index: 1198029 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5729. Min Act: -0.1700

Data Index: 2140410 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5533. Min Act: -0.1700

Data Index: 458926 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5112. Min Act: -0.1700

Data Index: 6068382 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5101. Min Act: -0.1700

Data Index: 846423 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5126. Min Act: -0.1700

Data Index: 1512113 (Open Web Text)

Max Activating Token Index: 982

Text #10

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5135. Min Act: -0.1700

Data Index: 5728671 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4952. Min Act: -0.1700

Data Index: 4351478 (Open Web Text)

Max Activating Token Index: 782

Text #12

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4860. Min Act: -0.1700

Data Index: 4013697 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.5032. Min Act: -0.1700

Data Index: 4947023 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4751. Min Act: -0.1700

Data Index: 5184267 (Open Web Text)

Max Activating Token Index: 764

Text #15

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4462. Min Act: -0.1700

Data Index: 6356013 (Open Web Text)

Max Activating Token Index: 725

Text #16

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4427. Min Act: -0.1700

Data Index: 128604 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4560. Min Act: -0.1700

Data Index: 8467118 (Open Web Text)

Max Activating Token Index: 553

Text #18

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4229. Min Act: -0.1700

Data Index: 2103954 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 3.7346. Min Range: -3.7346

Max Act: 3.4349. Min Act: -0.1700

Data Index: 4122168 (Open Web Text)

Max Activating Token Index: 31