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

Dataset: Open Web Text

Neuron 1703 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: 4.6256. Min Range: -4.6256

Max Act: 4.6256. Min Act: -0.1700

Data Index: 4464975 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.6020. Min Act: -0.1700

Data Index: 6579904 (Open Web Text)

Max Activating Token Index: 78

Text #2

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.5285. Min Act: -0.1700

Data Index: 2183059 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.5342. Min Act: -0.1700

Data Index: 6570162 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4480. Min Act: -0.1700

Data Index: 2665320 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4514. Min Act: -0.1700

Data Index: 8238653 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4244. Min Act: -0.1700

Data Index: 5129932 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4363. Min Act: -0.1700

Data Index: 1043945 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3991. Min Act: -0.1700

Data Index: 7163007 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3873. Min Act: -0.1700

Data Index: 1992056 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4121. Min Act: -0.1700

Data Index: 2872326 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3716. Min Act: -0.1700

Data Index: 3452929 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3784. Min Act: -0.1700

Data Index: 3371855 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3834. Min Act: -0.1700

Data Index: 4462163 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.4065. Min Act: -0.1700

Data Index: 3339707 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3945. Min Act: -0.1700

Data Index: 2931884 (Open Web Text)

Max Activating Token Index: 297

Text #16

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3655. Min Act: -0.1700

Data Index: 2385158 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3652. Min Act: -0.1700

Data Index: 1566927 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3607. Min Act: -0.1700

Data Index: 1828604 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.6256. Min Range: -4.6256

Max Act: 4.3697. Min Act: -0.1700

Data Index: 56001 (Open Web Text)

Max Activating Token Index: 896