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

Dataset: Open Web Text

Neuron 2535 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: 3.8885. Min Range: -3.8885

Max Act: 3.8885. Min Act: -0.1700

Data Index: 8393074 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8664. Min Act: -0.1700

Data Index: 7713960 (Open Web Text)

Max Activating Token Index: 290

Text #2

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8471. Min Act: -0.1700

Data Index: 2694043 (Open Web Text)

Max Activating Token Index: 291

Text #3

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8399. Min Act: -0.1700

Data Index: 5339789 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8808. Min Act: -0.1700

Data Index: 4289047 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8662. Min Act: -0.1700

Data Index: 862209 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8340. Min Act: -0.1700

Data Index: 4681768 (Open Web Text)

Max Activating Token Index: 262

Text #7

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8119. Min Act: -0.1700

Data Index: 2365984 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8129. Min Act: -0.1700

Data Index: 1486767 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.8131. Min Act: -0.1700

Data Index: 7025864 (Open Web Text)

Max Activating Token Index: 189

Text #10

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7913. Min Act: -0.1700

Data Index: 7124785 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7953. Min Act: -0.1700

Data Index: 8033936 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7856. Min Act: -0.1700

Data Index: 3882570 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7750. Min Act: -0.1700

Data Index: 3122474 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7770. Min Act: -0.1700

Data Index: 2406329 (Open Web Text)

Max Activating Token Index: 67

Text #15

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7611. Min Act: -0.1700

Data Index: 2156910 (Open Web Text)

Max Activating Token Index: 87

Text #16

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7688. Min Act: -0.1700

Data Index: 6596453 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1943114 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7716. Min Act: -0.1700

Data Index: 6758257 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.8885. Min Range: -3.8885

Max Act: 3.7719. Min Act: -0.1700

Data Index: 950266 (Open Web Text)

Max Activating Token Index: 52