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

Dataset: Open Web Text

Neuron 66 in Layer 2

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: 2.3826. Min Range: -2.3826

Max Act: 2.3826. Min Act: -0.1700

Data Index: 4783002 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3298. Min Act: -0.1700

Data Index: 5734579 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.3102. Min Act: -0.1700

Data Index: 8424709 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2891. Min Act: -0.1700

Data Index: 7742280 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2762. Min Act: -0.1700

Data Index: 5637973 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2699. Min Act: -0.1700

Data Index: 8001251 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2780. Min Act: -0.1700

Data Index: 5353173 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2476. Min Act: -0.1700

Data Index: 6162245 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2474. Min Act: -0.1700

Data Index: 2704523 (Open Web Text)

Max Activating Token Index: 906

Text #9

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2428. Min Act: -0.1700

Data Index: 1508980 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2067. Min Act: -0.1700

Data Index: 3596229 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1747. Min Act: -0.1700

Data Index: 8227299 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1892. Min Act: -0.1700

Data Index: 5877388 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2147. Min Act: -0.1700

Data Index: 5353183 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.2208. Min Act: -0.1700

Data Index: 1182364 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1902. Min Act: -0.1700

Data Index: 7117266 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1740. Min Act: -0.1700

Data Index: 2784340 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1822. Min Act: -0.1700

Data Index: 4079680 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1714. Min Act: -0.1700

Data Index: 8716248 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.3826. Min Range: -2.3826

Max Act: 2.1833. Min Act: -0.1700

Data Index: 1510125 (Open Web Text)

Max Activating Token Index: 1023