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

Dataset: Open Web Text

Neuron 2634 in Layer 3

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: 3.5987. Min Range: -3.5987

Max Act: 3.5987. Min Act: -0.1700

Data Index: 2750161 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2844. Min Act: -0.1700

Data Index: 2032845 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2883. Min Act: -0.1700

Data Index: 603400 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2806. Min Act: -0.1700

Data Index: 8131774 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2814. Min Act: -0.1700

Data Index: 2032848 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2688. Min Act: -0.1700

Data Index: 7120984 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2761. Min Act: -0.1700

Data Index: 6645344 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2412. Min Act: -0.1700

Data Index: 6383715 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2297. Min Act: -0.1700

Data Index: 471257 (Open Web Text)

Max Activating Token Index: 900

Text #9

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2358. Min Act: -0.1700

Data Index: 8362587 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2381. Min Act: -0.1700

Data Index: 4137951 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2358. Min Act: -0.1700

Data Index: 6524367 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2096. Min Act: -0.1700

Data Index: 2687376 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.2159. Min Act: -0.1700

Data Index: 8745307 (Open Web Text)

Max Activating Token Index: 570

Text #14

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1795. Min Act: -0.1700

Data Index: 1525667 (Open Web Text)

Max Activating Token Index: 224

Text #15

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1885. Min Act: -0.1700

Data Index: 1501313 (Open Web Text)

Max Activating Token Index: 346

Text #16

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1895. Min Act: -0.1700

Data Index: 3802404 (Open Web Text)

Max Activating Token Index: 54

Text #17

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1878. Min Act: -0.1700

Data Index: 5941917 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1616. Min Act: -0.1700

Data Index: 495291 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 3.5987. Min Range: -3.5987

Max Act: 3.1749. Min Act: -0.1700

Data Index: 275845 (Open Web Text)

Max Activating Token Index: 528