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

Dataset: Open Web Text

Neuron 1400 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: 3.4924. Min Range: -3.4924

Max Act: 3.4924. Min Act: -0.1700

Data Index: 4206269 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4119. Min Act: -0.1700

Data Index: 54928 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3882. Min Act: -0.1700

Data Index: 7343801 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4189. Min Act: -0.1700

Data Index: 2399102 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3739. Min Act: -0.1700

Data Index: 4192737 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3739. Min Act: -0.1700

Data Index: 7767347 (Open Web Text)

Max Activating Token Index: 159

Text #6

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3333. Min Act: -0.1700

Data Index: 5462166 (Open Web Text)

Max Activating Token Index: 822

Text #7

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3540. Min Act: -0.1700

Data Index: 4813710 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3446. Min Act: -0.1700

Data Index: 6164812 (Open Web Text)

Max Activating Token Index: 770

Text #9

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3707. Min Act: -0.1700

Data Index: 1813752 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3275. Min Act: -0.1700

Data Index: 1315120 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.4196. Min Act: -0.1700

Data Index: 2655982 (Open Web Text)

Max Activating Token Index: 1000

Text #12

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3281. Min Act: -0.1700

Data Index: 3350209 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3575. Min Act: -0.1700

Data Index: 1376416 (Open Web Text)

Max Activating Token Index: 954

Text #14

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3457. Min Act: -0.1700

Data Index: 6249774 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3382. Min Act: -0.1700

Data Index: 5417970 (Open Web Text)

Max Activating Token Index: 717

Text #16

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3479. Min Act: -0.1700

Data Index: 1054598 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3205. Min Act: -0.1700

Data Index: 3361317 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3711. Min Act: -0.1700

Data Index: 7095391 (Open Web Text)

Max Activating Token Index: 576

Text #19

Max Range: 3.4924. Min Range: -3.4924

Max Act: 3.3517. Min Act: -0.1700

Data Index: 624817 (Open Web Text)

Max Activating Token Index: 922