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

Dataset: Open Web Text

Neuron 69 in Layer 5

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: 3.2186. Min Range: -3.2186

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1759205 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.2036. Min Act: -0.1700

Data Index: 1776296 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1861. Min Act: -0.1700

Data Index: 5325494 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1618. Min Act: -0.1700

Data Index: 2032960 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1584. Min Act: -0.1700

Data Index: 5244890 (Open Web Text)

Max Activating Token Index: 618

Text #5

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1859. Min Act: -0.1700

Data Index: 7420792 (Open Web Text)

Max Activating Token Index: 440

Text #6

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1307. Min Act: -0.1700

Data Index: 8120343 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1363. Min Act: -0.1700

Data Index: 7629054 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1235. Min Act: -0.1700

Data Index: 4133505 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0885. Min Act: -0.1700

Data Index: 6869990 (Open Web Text)

Max Activating Token Index: 866

Text #10

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0904. Min Act: -0.1700

Data Index: 971837 (Open Web Text)

Max Activating Token Index: 723

Text #11

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0979. Min Act: -0.1700

Data Index: 8709185 (Open Web Text)

Max Activating Token Index: 350

Text #12

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.1074. Min Act: -0.1700

Data Index: 4018281 (Open Web Text)

Max Activating Token Index: 914

Text #13

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0696. Min Act: -0.1700

Data Index: 8355797 (Open Web Text)

Max Activating Token Index: 340

Text #14

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0817. Min Act: -0.1700

Data Index: 8452544 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0688. Min Act: -0.1700

Data Index: 4802747 (Open Web Text)

Max Activating Token Index: 585

Text #16

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0639. Min Act: -0.1700

Data Index: 859145 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0605. Min Act: -0.1700

Data Index: 8612645 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0785. Min Act: -0.1700

Data Index: 5808965 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.2186. Min Range: -3.2186

Max Act: 3.0586. Min Act: -0.1700

Data Index: 2976696 (Open Web Text)

Max Activating Token Index: 395