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

Dataset: Open Web Text

Neuron 3008 in Layer 0

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: 0.7530. Min Range: -0.7530

Max Act: 0.7530. Min Act: -0.1700

Data Index: 7947988 (Open Web Text)

Max Activating Token Index: 265

Text #1

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7409. Min Act: -0.1700

Data Index: 6824197 (Open Web Text)

Max Activating Token Index: 851

Text #2

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7162. Min Act: -0.1700

Data Index: 1196412 (Open Web Text)

Max Activating Token Index: 909

Text #3

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7215. Min Act: -0.1700

Data Index: 7653695 (Open Web Text)

Max Activating Token Index: 756

Text #4

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7191. Min Act: -0.1700

Data Index: 7184538 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7050. Min Act: -0.1700

Data Index: 3550125 (Open Web Text)

Max Activating Token Index: 832

Text #6

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7040. Min Act: -0.1700

Data Index: 1870550 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6980. Min Act: -0.1700

Data Index: 3378987 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6897. Min Act: -0.1700

Data Index: 2603801 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6936. Min Act: -0.1700

Data Index: 303595 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6912. Min Act: -0.1700

Data Index: 2650998 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6932. Min Act: -0.1700

Data Index: 232700 (Open Web Text)

Max Activating Token Index: 812

Text #12

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.7028. Min Act: -0.1700

Data Index: 5264484 (Open Web Text)

Max Activating Token Index: 392

Text #13

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6807. Min Act: -0.1700

Data Index: 8437161 (Open Web Text)

Max Activating Token Index: 731

Text #14

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6901. Min Act: -0.1700

Data Index: 407651 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6938. Min Act: -0.1700

Data Index: 6495398 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6854. Min Act: -0.1700

Data Index: 1639691 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6930. Min Act: -0.1700

Data Index: 3276223 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6776. Min Act: -0.1700

Data Index: 554451 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 0.7530. Min Range: -0.7530

Max Act: 0.6700. Min Act: -0.1700

Data Index: 3782322 (Open Web Text)

Max Activating Token Index: 264