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

Dataset: Open Web Text

Neuron 2735 in Layer 0

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: 4.7396. Min Range: -4.7396

Max Act: 4.7396. Min Act: -0.1700

Data Index: 3575114 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.7235. Min Act: -0.1700

Data Index: 793445 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.7261. Min Act: -0.1700

Data Index: 1219288 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6946. Min Act: -0.1700

Data Index: 6224162 (Open Web Text)

Max Activating Token Index: 964

Text #4

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6762. Min Act: -0.1700

Data Index: 1823961 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6827. Min Act: -0.1700

Data Index: 7033959 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6670. Min Act: -0.1700

Data Index: 6215552 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6455. Min Act: -0.1700

Data Index: 2457030 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6348. Min Act: -0.1700

Data Index: 8705023 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6176. Min Act: -0.1700

Data Index: 454890 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6215. Min Act: -0.1700

Data Index: 1067359 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6090. Min Act: -0.1700

Data Index: 7589565 (Open Web Text)

Max Activating Token Index: 653

Text #12

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6228. Min Act: -0.1700

Data Index: 7451359 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6361. Min Act: -0.1700

Data Index: 7227193 (Open Web Text)

Max Activating Token Index: 979

Text #14

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6200. Min Act: -0.1700

Data Index: 1548722 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6367. Min Act: -0.1700

Data Index: 7130517 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6374. Min Act: -0.1700

Data Index: 2313029 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6126. Min Act: -0.1700

Data Index: 3425986 (Open Web Text)

Max Activating Token Index: 1002

Text #18

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6218. Min Act: -0.1700

Data Index: 7022127 (Open Web Text)

Max Activating Token Index: 732

Text #19

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6398. Min Act: -0.1700

Data Index: 219109 (Open Web Text)

Max Activating Token Index: 16