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

Dataset: Open Web Text

Neuron 2405 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: 3.7857. Min Range: -3.7857

Max Act: 3.7857. Min Act: -0.1700

Data Index: 6913494 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.7317. Min Act: -0.1700

Data Index: 2949074 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.7085. Min Act: -0.1700

Data Index: 447321 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.7638. Min Act: -0.1700

Data Index: 522054 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.7051. Min Act: -0.1700

Data Index: 5455079 (Open Web Text)

Max Activating Token Index: 437

Text #5

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6729. Min Act: -0.1700

Data Index: 7901004 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6662. Min Act: -0.1700

Data Index: 104620 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6177. Min Act: -0.1700

Data Index: 6166044 (Open Web Text)

Max Activating Token Index: 220

Text #8

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6132. Min Act: -0.1700

Data Index: 7610589 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6134. Min Act: -0.1700

Data Index: 5394634 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6122. Min Act: -0.1700

Data Index: 6035065 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.5851. Min Act: -0.1700

Data Index: 5365981 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6024. Min Act: -0.1700

Data Index: 3111058 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6151. Min Act: -0.1700

Data Index: 6203801 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6126. Min Act: -0.1700

Data Index: 7670938 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.6111. Min Act: -0.1700

Data Index: 6203799 (Open Web Text)

Max Activating Token Index: 334

Text #16

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.5558. Min Act: -0.1700

Data Index: 3820529 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.5817. Min Act: -0.1700

Data Index: 7277910 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.5780. Min Act: -0.1700

Data Index: 3936093 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 3.7857. Min Range: -3.7857

Max Act: 3.5433. Min Act: -0.1700

Data Index: 4675336 (Open Web Text)

Max Activating Token Index: 702