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

Dataset: Open Web Text

Neuron 2576 in Layer 3

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: 4.8576. Min Range: -4.8576

Max Act: 4.8576. Min Act: -0.1700

Data Index: 620694 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.8567. Min Act: -0.1700

Data Index: 2230571 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.8312. Min Act: -0.1700

Data Index: 7883552 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.7527. Min Act: -0.1700

Data Index: 3629987 (Open Web Text)

Max Activating Token Index: 55

Text #4

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.7617. Min Act: -0.1700

Data Index: 7458427 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.7617. Min Act: -0.1700

Data Index: 1053452 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.7113. Min Act: -0.1700

Data Index: 7869575 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5954. Min Act: -0.1700

Data Index: 5310070 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.6509. Min Act: -0.1700

Data Index: 1803610 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.6348. Min Act: -0.1700

Data Index: 6791103 (Open Web Text)

Max Activating Token Index: 326

Text #10

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.6124. Min Act: -0.1700

Data Index: 1459169 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5965. Min Act: -0.1700

Data Index: 442828 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5996. Min Act: -0.1700

Data Index: 8241734 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5783. Min Act: -0.1700

Data Index: 2725838 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5691. Min Act: -0.1700

Data Index: 1032382 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5573. Min Act: -0.1700

Data Index: 1509747 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5914. Min Act: -0.1700

Data Index: 5175508 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5584. Min Act: -0.1700

Data Index: 7254551 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5853. Min Act: -0.1700

Data Index: 1570582 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 4.8576. Min Range: -4.8576

Max Act: 4.5242. Min Act: -0.1700

Data Index: 1385015 (Open Web Text)

Max Activating Token Index: 942