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

Dataset: Open Web Text

Neuron 320 in Layer 1

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: 2.1780. Min Range: -2.1780

Max Act: 2.1780. Min Act: -0.1700

Data Index: 8555192 (Open Web Text)

Max Activating Token Index: 964

Text #1

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1748. Min Act: -0.1700

Data Index: 1391251 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1519. Min Act: -0.1700

Data Index: 8528394 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1491. Min Act: -0.1700

Data Index: 8660483 (Open Web Text)

Max Activating Token Index: 942

Text #4

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1416. Min Act: -0.1700

Data Index: 4222335 (Open Web Text)

Max Activating Token Index: 160

Text #5

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1539. Min Act: -0.1700

Data Index: 2264677 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1225. Min Act: -0.1700

Data Index: 8143059 (Open Web Text)

Max Activating Token Index: 894

Text #7

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1408. Min Act: -0.1700

Data Index: 5467401 (Open Web Text)

Max Activating Token Index: 742

Text #8

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1376. Min Act: -0.1700

Data Index: 847068 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1187. Min Act: -0.1700

Data Index: 5886638 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1119. Min Act: -0.1700

Data Index: 7008166 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1047. Min Act: -0.1700

Data Index: 6759836 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1068. Min Act: -0.1700

Data Index: 3869096 (Open Web Text)

Max Activating Token Index: 883

Text #13

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1230. Min Act: -0.1700

Data Index: 5797241 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1108. Min Act: -0.1700

Data Index: 3273402 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1126. Min Act: -0.1700

Data Index: 497550 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.0991. Min Act: -0.1700

Data Index: 690583 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.1010. Min Act: -0.1700

Data Index: 549779 (Open Web Text)

Max Activating Token Index: 172

Text #18

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.0994. Min Act: -0.1700

Data Index: 7930406 (Open Web Text)

Max Activating Token Index: 1000

Text #19

Max Range: 2.1780. Min Range: -2.1780

Max Act: 2.0993. Min Act: -0.1700

Data Index: 1512113 (Open Web Text)

Max Activating Token Index: 888