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

Dataset: Open Web Text

Neuron 2391 in Layer 5

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: 4.4215. Min Range: -4.4215

Max Act: 4.4215. Min Act: -0.1700

Data Index: 5262128 (Open Web Text)

Max Activating Token Index: 720

Text #1

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.1974. Min Act: -0.1700

Data Index: 2926269 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.1824. Min Act: -0.1700

Data Index: 109734 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.1259. Min Act: -0.1700

Data Index: 1270485 (Open Web Text)

Max Activating Token Index: 794

Text #4

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.1356. Min Act: -0.1700

Data Index: 5543045 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.0275. Min Act: -0.1700

Data Index: 75734 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 4.4215. Min Range: -4.4215

Max Act: 4.0075. Min Act: -0.1700

Data Index: 8236746 (Open Web Text)

Max Activating Token Index: 752

Text #7

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.9957. Min Act: -0.1700

Data Index: 6272998 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.9448. Min Act: -0.1700

Data Index: 7442611 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8954. Min Act: -0.1700

Data Index: 7989023 (Open Web Text)

Max Activating Token Index: 849

Text #10

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.9106. Min Act: -0.1700

Data Index: 3765075 (Open Web Text)

Max Activating Token Index: 852

Text #11

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.9174. Min Act: -0.1700

Data Index: 2898704 (Open Web Text)

Max Activating Token Index: 985

Text #12

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8776. Min Act: -0.1700

Data Index: 1015644 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8699. Min Act: -0.1700

Data Index: 1640331 (Open Web Text)

Max Activating Token Index: 903

Text #14

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8959. Min Act: -0.1700

Data Index: 8374631 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8296. Min Act: -0.1700

Data Index: 5651145 (Open Web Text)

Max Activating Token Index: 919

Text #16

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8617. Min Act: -0.1700

Data Index: 1194839 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8577. Min Act: -0.1700

Data Index: 8543330 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8326. Min Act: -0.1700

Data Index: 6412812 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 4.4215. Min Range: -4.4215

Max Act: 3.8131. Min Act: -0.1700

Data Index: 6990258 (Open Web Text)

Max Activating Token Index: 327