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

Dataset: Open Web Text

Neuron 2168 in Layer 0

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: 3.9028. Min Range: -3.9028

Max Act: 3.8808. Min Act: -0.1700

Data Index: 4167282 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.9028. Min Act: -0.1700

Data Index: 1826133 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8438. Min Act: -0.1700

Data Index: 2825408 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8315. Min Act: -0.1700

Data Index: 8008239 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8311. Min Act: -0.1700

Data Index: 4989714 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.8009. Min Act: -0.1700

Data Index: 3694318 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7874. Min Act: -0.1700

Data Index: 6109811 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7992. Min Act: -0.1700

Data Index: 8801419 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7889. Min Act: -0.1700

Data Index: 2825402 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7909. Min Act: -0.1700

Data Index: 8378464 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1704852 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7612. Min Act: -0.1700

Data Index: 1765658 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7167. Min Act: -0.1700

Data Index: 2825406 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7433. Min Act: -0.1700

Data Index: 8523043 (Open Web Text)

Max Activating Token Index: 62

Text #14

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7153. Min Act: -0.1700

Data Index: 2721610 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7352. Min Act: -0.1700

Data Index: 1026731 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7007. Min Act: -0.1700

Data Index: 8030827 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7102. Min Act: -0.1700

Data Index: 441411 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7079. Min Act: -0.1700

Data Index: 7741082 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 3.9028. Min Range: -3.9028

Max Act: 3.7018. Min Act: -0.1700

Data Index: 7196193 (Open Web Text)

Max Activating Token Index: 48