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

Dataset: Open Web Text

Neuron 1245 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: 3.3075. Min Range: -3.3075

Max Act: 3.3075. Min Act: -0.1700

Data Index: 5517935 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2819. Min Act: -0.1700

Data Index: 565006 (Open Web Text)

Max Activating Token Index: 564

Text #2

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2781. Min Act: -0.1700

Data Index: 4797868 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2365. Min Act: -0.1700

Data Index: 7873247 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2362. Min Act: -0.1700

Data Index: 685402 (Open Web Text)

Max Activating Token Index: 191

Text #5

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2191. Min Act: -0.1700

Data Index: 5229903 (Open Web Text)

Max Activating Token Index: 328

Text #6

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2080. Min Act: -0.1700

Data Index: 8578757 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2345. Min Act: -0.1700

Data Index: 461610 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1987. Min Act: -0.1700

Data Index: 3498924 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1854. Min Act: -0.1700

Data Index: 4069524 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1932. Min Act: -0.1700

Data Index: 8030346 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1891. Min Act: -0.1700

Data Index: 8436790 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1781. Min Act: -0.1700

Data Index: 8181033 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1844. Min Act: -0.1700

Data Index: 1534138 (Open Web Text)

Max Activating Token Index: 423

Text #14

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1928. Min Act: -0.1700

Data Index: 2146808 (Open Web Text)

Max Activating Token Index: 644

Text #15

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2022. Min Act: -0.1700

Data Index: 1262333 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1757. Min Act: -0.1700

Data Index: 2721708 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1815. Min Act: -0.1700

Data Index: 7741819 (Open Web Text)

Max Activating Token Index: 160

Text #18

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1622. Min Act: -0.1700

Data Index: 7581557 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1499. Min Act: -0.1700

Data Index: 7535250 (Open Web Text)

Max Activating Token Index: 288