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

Dataset: Open Web Text

Neuron 2562 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: 3.3594. Min Range: -3.3594

Max Act: 3.3459. Min Act: -0.1700

Data Index: 4963294 (Open Web Text)

Max Activating Token Index: 463

Text #1

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.3594. Min Act: -0.1700

Data Index: 154474 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.3073. Min Act: -0.1700

Data Index: 1755029 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2786. Min Act: -0.1700

Data Index: 1205252 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2476. Min Act: -0.1700

Data Index: 5037535 (Open Web Text)

Max Activating Token Index: 975

Text #5

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2419. Min Act: -0.1700

Data Index: 4741040 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2201. Min Act: -0.1700

Data Index: 2334673 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2477. Min Act: -0.1700

Data Index: 5004956 (Open Web Text)

Max Activating Token Index: 731

Text #8

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2227. Min Act: -0.1700

Data Index: 937574 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2034. Min Act: -0.1700

Data Index: 820177 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1977. Min Act: -0.1700

Data Index: 6953249 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2078. Min Act: -0.1700

Data Index: 7528482 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1980. Min Act: -0.1700

Data Index: 1279683 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2126. Min Act: -0.1700

Data Index: 4469472 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2030. Min Act: -0.1700

Data Index: 113962 (Open Web Text)

Max Activating Token Index: 995

Text #15

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.2058. Min Act: -0.1700

Data Index: 3273427 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1716. Min Act: -0.1700

Data Index: 3740224 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1822. Min Act: -0.1700

Data Index: 2322850 (Open Web Text)

Max Activating Token Index: 406

Text #18

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1881. Min Act: -0.1700

Data Index: 132941 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 3.3594. Min Range: -3.3594

Max Act: 3.1885. Min Act: -0.1700

Data Index: 3116144 (Open Web Text)

Max Activating Token Index: 405