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

Dataset: Open Web Text

Neuron 1862 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: 2.1054. Min Range: -2.1054

Max Act: 2.1054. Min Act: -0.1700

Data Index: 6006738 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 2.1054. Min Range: -2.1054

Max Act: 2.0037. Min Act: -0.1700

Data Index: 5790691 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8502. Min Act: -0.1700

Data Index: 5964069 (Open Web Text)

Max Activating Token Index: 519

Text #3

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8254. Min Act: -0.1700

Data Index: 2854521 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8328. Min Act: -0.1700

Data Index: 2774392 (Open Web Text)

Max Activating Token Index: 183

Text #5

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8351. Min Act: -0.1700

Data Index: 1772677 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8240. Min Act: -0.1700

Data Index: 688526 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8292. Min Act: -0.1700

Data Index: 221735 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8121. Min Act: -0.1700

Data Index: 249044 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8193. Min Act: -0.1700

Data Index: 2782219 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8301. Min Act: -0.1700

Data Index: 1735211 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8312. Min Act: -0.1700

Data Index: 5314711 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8200. Min Act: -0.1700

Data Index: 430345 (Open Web Text)

Max Activating Token Index: 939

Text #13

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8039. Min Act: -0.1700

Data Index: 8624345 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8144. Min Act: -0.1700

Data Index: 8332680 (Open Web Text)

Max Activating Token Index: 654

Text #15

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.8159. Min Act: -0.1700

Data Index: 4657184 (Open Web Text)

Max Activating Token Index: 853

Text #16

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7898. Min Act: -0.1700

Data Index: 3689258 (Open Web Text)

Max Activating Token Index: 74

Text #17

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7675. Min Act: -0.1700

Data Index: 7443920 (Open Web Text)

Max Activating Token Index: 618

Text #18

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7774. Min Act: -0.1700

Data Index: 5446744 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 2.1054. Min Range: -2.1054

Max Act: 1.7779. Min Act: -0.1700

Data Index: 1142791 (Open Web Text)

Max Activating Token Index: 796