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

Dataset: Open Web Text

Neuron 2711 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: 1.3991. Min Range: -1.3991

Max Act: 1.3824. Min Act: -0.1700

Data Index: 6736301 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.3991. Min Act: -0.1700

Data Index: 4317708 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.3312. Min Act: -0.1700

Data Index: 5497307 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.3167. Min Act: -0.1700

Data Index: 7875173 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.3323. Min Act: -0.1700

Data Index: 6475823 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2667. Min Act: -0.1700

Data Index: 4353180 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1586. Min Act: -0.1700

Data Index: 8169991 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.2455. Min Act: -0.1700

Data Index: 7726722 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1912. Min Act: -0.1700

Data Index: 4728412 (Open Web Text)

Max Activating Token Index: 480

Text #9

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1885. Min Act: -0.1700

Data Index: 4506896 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1764. Min Act: -0.1700

Data Index: 3481443 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.0559. Min Act: -0.1700

Data Index: 8569223 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1205. Min Act: -0.1700

Data Index: 5568982 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.0982. Min Act: -0.1700

Data Index: 6173999 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1740. Min Act: -0.1700

Data Index: 4852819 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1849. Min Act: -0.1700

Data Index: 8419786 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1637. Min Act: -0.1700

Data Index: 6201217 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1534. Min Act: -0.1700

Data Index: 3814799 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1534. Min Act: -0.1700

Data Index: 4025762 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.3991. Min Range: -1.3991

Max Act: 1.1534. Min Act: -0.1700

Data Index: 4176434 (Open Web Text)

Max Activating Token Index: 1