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

Dataset: Open Web Text

Neuron 1280 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: 0.8632. Min Range: -0.8632

Max Act: 0.8632. Min Act: -0.1403

Data Index: 6539776 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8615. Min Act: -0.1338

Data Index: 8137254 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8525. Min Act: -0.1492

Data Index: 4386975 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8501. Min Act: -0.1337

Data Index: 784695 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8378. Min Act: -0.0455

Data Index: 4294795 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8438. Min Act: -0.1476

Data Index: 5259063 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8398. Min Act: -0.0907

Data Index: 264107 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8268. Min Act: -0.1549

Data Index: 6449847 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8173. Min Act: -0.1304

Data Index: 8590039 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8093. Min Act: -0.1067

Data Index: 601060 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8243. Min Act: -0.1373

Data Index: 1899549 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8217. Min Act: 0.0276

Data Index: 2913765 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8052. Min Act: -0.1206

Data Index: 3446443 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8080. Min Act: -0.0942

Data Index: 3419040 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8118. Min Act: -0.1074

Data Index: 1534550 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8073. Min Act: -0.1576

Data Index: 24356 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8067. Min Act: -0.1619

Data Index: 5870882 (Open Web Text)

Max Activating Token Index: 375

Text #17

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8072. Min Act: -0.1173

Data Index: 1754912 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8055. Min Act: -0.1334

Data Index: 5821885 (Open Web Text)

Max Activating Token Index: 722

Text #19

Max Range: 0.8632. Min Range: -0.8632

Max Act: 0.8074. Min Act: -0.0545

Data Index: 2778879 (Open Web Text)

Max Activating Token Index: 34