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

Dataset: Open Web Text

Neuron 1507 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: 2.9237. Min Range: -2.9237

Max Act: 2.9237. Min Act: -0.1700

Data Index: 4564803 (Open Web Text)

Max Activating Token Index: 513

Text #1

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.8293. Min Act: -0.1700

Data Index: 2216059 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.6737. Min Act: -0.1700

Data Index: 2233424 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.6493. Min Act: -0.1700

Data Index: 2233425 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5749. Min Act: -0.1700

Data Index: 4645322 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5517. Min Act: -0.1700

Data Index: 2153469 (Open Web Text)

Max Activating Token Index: 731

Text #6

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5593. Min Act: -0.1700

Data Index: 2901570 (Open Web Text)

Max Activating Token Index: 250

Text #7

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5552. Min Act: -0.1700

Data Index: 8737336 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5326. Min Act: -0.1700

Data Index: 2554146 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5466. Min Act: -0.1700

Data Index: 3475471 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5200. Min Act: -0.1700

Data Index: 1247711 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5204. Min Act: -0.1700

Data Index: 2153468 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5059. Min Act: -0.1700

Data Index: 4720290 (Open Web Text)

Max Activating Token Index: 974

Text #13

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5129. Min Act: -0.1700

Data Index: 6390110 (Open Web Text)

Max Activating Token Index: 399

Text #14

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4999. Min Act: -0.1700

Data Index: 3733581 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5204. Min Act: -0.1700

Data Index: 1683193 (Open Web Text)

Max Activating Token Index: 890

Text #16

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4881. Min Act: -0.1700

Data Index: 2233422 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5024. Min Act: -0.1700

Data Index: 4517792 (Open Web Text)

Max Activating Token Index: 890

Text #18

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5055. Min Act: -0.1700

Data Index: 2554145 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5068. Min Act: -0.1700

Data Index: 1684753 (Open Web Text)

Max Activating Token Index: 782