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

Dataset: Open Web Text

Neuron 1000 in Layer 5

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: 4.7295. Min Range: -4.7295

Max Act: 4.7295. Min Act: -0.1700

Data Index: 927973 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.6432. Min Act: -0.1700

Data Index: 3043665 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.6581. Min Act: -0.1700

Data Index: 3043667 (Open Web Text)

Max Activating Token Index: 104

Text #3

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.6871. Min Act: -0.1700

Data Index: 2968295 (Open Web Text)

Max Activating Token Index: 1020

Text #4

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.6109. Min Act: -0.1700

Data Index: 6272702 (Open Web Text)

Max Activating Token Index: 378

Text #5

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.5218. Min Act: -0.1700

Data Index: 2299422 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.5193. Min Act: -0.1700

Data Index: 2284227 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.5339. Min Act: -0.1700

Data Index: 6595800 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.5190. Min Act: -0.1700

Data Index: 724021 (Open Web Text)

Max Activating Token Index: 524

Text #9

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4964. Min Act: -0.1700

Data Index: 6623735 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4985. Min Act: -0.1700

Data Index: 4218513 (Open Web Text)

Max Activating Token Index: 799

Text #11

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4969. Min Act: -0.1700

Data Index: 2853616 (Open Web Text)

Max Activating Token Index: 568

Text #12

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4735. Min Act: -0.1700

Data Index: 8749703 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4853. Min Act: -0.1700

Data Index: 6035549 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4475. Min Act: -0.1700

Data Index: 4572986 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4728. Min Act: -0.1700

Data Index: 7222909 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4965. Min Act: -0.1700

Data Index: 7467245 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4378. Min Act: -0.1700

Data Index: 920555 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4922. Min Act: -0.1700

Data Index: 8188616 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 4.7295. Min Range: -4.7295

Max Act: 4.4540. Min Act: -0.1700

Data Index: 5182704 (Open Web Text)

Max Activating Token Index: 211