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

Dataset: Open Web Text

Neuron 2816 in Layer 6

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: 5.0398. Min Range: -5.0398

Max Act: 5.0398. Min Act: -0.1700

Data Index: 2517552 (Open Web Text)

Max Activating Token Index: 190

Text #1

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.8957. Min Act: -0.1700

Data Index: 607290 (Open Web Text)

Max Activating Token Index: 199

Text #2

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.8561. Min Act: -0.1700

Data Index: 184790 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7845. Min Act: -0.1700

Data Index: 3346906 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.8220. Min Act: -0.1700

Data Index: 4925644 (Open Web Text)

Max Activating Token Index: 610

Text #5

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7766. Min Act: -0.1700

Data Index: 406324 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7397. Min Act: -0.1700

Data Index: 2571200 (Open Web Text)

Max Activating Token Index: 707

Text #7

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7270. Min Act: -0.1700

Data Index: 8285139 (Open Web Text)

Max Activating Token Index: 634

Text #8

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.6995. Min Act: -0.1700

Data Index: 4169733 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7148. Min Act: -0.1700

Data Index: 4102474 (Open Web Text)

Max Activating Token Index: 739

Text #10

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.6988. Min Act: -0.1700

Data Index: 6193057 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7450. Min Act: -0.1700

Data Index: 8740274 (Open Web Text)

Max Activating Token Index: 849

Text #12

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7206. Min Act: -0.1700

Data Index: 7869719 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7229. Min Act: -0.1700

Data Index: 7431634 (Open Web Text)

Max Activating Token Index: 965

Text #14

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7490. Min Act: -0.1700

Data Index: 7263703 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7046. Min Act: -0.1700

Data Index: 4690475 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.6835. Min Act: -0.1700

Data Index: 1853325 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.6974. Min Act: -0.1700

Data Index: 2593393 (Open Web Text)

Max Activating Token Index: 200

Text #18

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.6772. Min Act: -0.1700

Data Index: 8801227 (Open Web Text)

Max Activating Token Index: 549

Text #19

Max Range: 5.0398. Min Range: -5.0398

Max Act: 4.7307. Min Act: -0.1700

Data Index: 357987 (Open Web Text)

Max Activating Token Index: 32