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

Dataset: Open Web Text

Neuron 2483 in Layer 4

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: 3.1814. Min Range: -3.1814

Max Act: 3.1814. Min Act: -0.1700

Data Index: 5250755 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1518. Min Act: -0.1700

Data Index: 3215316 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1543. Min Act: -0.1700

Data Index: 5323375 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1429. Min Act: -0.1700

Data Index: 3650121 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1423. Min Act: -0.1700

Data Index: 8679061 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1303. Min Act: -0.1700

Data Index: 7692503 (Open Web Text)

Max Activating Token Index: 709

Text #6

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1387. Min Act: -0.1700

Data Index: 6362740 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1053. Min Act: -0.1700

Data Index: 2576781 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1032. Min Act: -0.1700

Data Index: 2875559 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0965. Min Act: -0.1700

Data Index: 7658000 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.1078. Min Act: -0.1700

Data Index: 3242815 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0970. Min Act: -0.1700

Data Index: 1758703 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0982. Min Act: -0.1700

Data Index: 405262 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0944. Min Act: -0.1700

Data Index: 2309243 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0759. Min Act: -0.1700

Data Index: 2054512 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0780. Min Act: -0.1700

Data Index: 4610713 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0639. Min Act: -0.1700

Data Index: 5300990 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0657. Min Act: -0.1700

Data Index: 5068623 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0787. Min Act: -0.1700

Data Index: 3819255 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 3.1814. Min Range: -3.1814

Max Act: 3.0570. Min Act: -0.1700

Data Index: 67682 (Open Web Text)

Max Activating Token Index: 734