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

Dataset: Open Web Text

Neuron 2709 in Layer 4

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: 1.4575. Min Range: -1.4575

Max Act: 1.4575. Min Act: -0.1700

Data Index: 2205717 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2321. Min Act: -0.1700

Data Index: 1497130 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2105. Min Act: -0.1700

Data Index: 8746510 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2177. Min Act: -0.1700

Data Index: 1810948 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1637. Min Act: -0.1700

Data Index: 8478842 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1820. Min Act: -0.1700

Data Index: 5351481 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1263. Min Act: -0.1700

Data Index: 2657174 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1101. Min Act: -0.1700

Data Index: 3918524 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0792. Min Act: -0.1700

Data Index: 997786 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0996. Min Act: -0.1700

Data Index: 8185712 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.9656. Min Act: -0.1700

Data Index: 6400951 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.9865. Min Act: -0.1700

Data Index: 938280 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.9539. Min Act: -0.1700

Data Index: 2304737 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.8573. Min Act: -0.1700

Data Index: 2321449 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.8332. Min Act: -0.1700

Data Index: 6169708 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.7902. Min Act: -0.1700

Data Index: 1377246 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.7357. Min Act: -0.1700

Data Index: 4621765 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.7838. Min Act: -0.1700

Data Index: 8515206 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.7819. Min Act: -0.1700

Data Index: 6146017 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.4575. Min Range: -1.4575

Max Act: 0.6950. Min Act: -0.1700

Data Index: 851696 (Open Web Text)

Max Activating Token Index: 1023