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

Dataset: Open Web Text

Neuron 3029 in Layer 4

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: 3.4335. Min Range: -3.4335

Max Act: 3.4335. Min Act: -0.1700

Data Index: 6927511 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3842. Min Act: -0.1700

Data Index: 8353977 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3819. Min Act: -0.1700

Data Index: 6094830 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.4102. Min Act: -0.1700

Data Index: 4204936 (Open Web Text)

Max Activating Token Index: 583

Text #4

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3442. Min Act: -0.1700

Data Index: 6682865 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3697. Min Act: -0.1700

Data Index: 3501125 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3156. Min Act: -0.1700

Data Index: 2199879 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3415. Min Act: -0.1700

Data Index: 4416841 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2964. Min Act: -0.1700

Data Index: 4031511 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3198. Min Act: -0.1700

Data Index: 337171 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3147. Min Act: -0.1700

Data Index: 3098153 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3167. Min Act: -0.1700

Data Index: 3246975 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2719. Min Act: -0.1700

Data Index: 5971385 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3053. Min Act: -0.1700

Data Index: 3100756 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.3158. Min Act: -0.1700

Data Index: 6257650 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2876. Min Act: -0.1700

Data Index: 8545091 (Open Web Text)

Max Activating Token Index: 732

Text #16

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2754. Min Act: -0.1700

Data Index: 4160534 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2995. Min Act: -0.1700

Data Index: 3743424 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2874. Min Act: -0.1700

Data Index: 7303486 (Open Web Text)

Max Activating Token Index: 354

Text #19

Max Range: 3.4335. Min Range: -3.4335

Max Act: 3.2951. Min Act: -0.1700

Data Index: 896792 (Open Web Text)

Max Activating Token Index: 455