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

Dataset: Open Web Text

Neuron 3003 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: 2.8738. Min Range: -2.8738

Max Act: 2.8738. Min Act: -0.1700

Data Index: 5006321 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8374. Min Act: -0.1700

Data Index: 1080119 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8146. Min Act: -0.1700

Data Index: 8742616 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8302. Min Act: -0.1700

Data Index: 7263794 (Open Web Text)

Max Activating Token Index: 808

Text #4

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8198. Min Act: -0.1700

Data Index: 5992333 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8321. Min Act: -0.1700

Data Index: 3050234 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8157. Min Act: -0.1700

Data Index: 7186256 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8321. Min Act: -0.1700

Data Index: 1389979 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8130. Min Act: -0.1700

Data Index: 6872555 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8086. Min Act: -0.1700

Data Index: 4396042 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.8018. Min Act: -0.1700

Data Index: 3343638 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7750. Min Act: -0.1700

Data Index: 6479470 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7773. Min Act: -0.1700

Data Index: 3812261 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7743. Min Act: -0.1700

Data Index: 4746730 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7728. Min Act: -0.1700

Data Index: 4589718 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7751. Min Act: -0.1700

Data Index: 3585199 (Open Web Text)

Max Activating Token Index: 30

Text #16

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7780. Min Act: -0.1700

Data Index: 8103567 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7620. Min Act: -0.1700

Data Index: 7879079 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7603. Min Act: -0.1700

Data Index: 8793572 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 2.8738. Min Range: -2.8738

Max Act: 2.7534. Min Act: -0.1700

Data Index: 5959030 (Open Web Text)

Max Activating Token Index: 66