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

Dataset: Open Web Text

Neuron 1699 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: 4.8775. Min Range: -4.8775

Max Act: 4.8775. Min Act: -0.1700

Data Index: 1132659 (Open Web Text)

Max Activating Token Index: 961

Text #1

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7615. Min Act: -0.1700

Data Index: 2106162 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7285. Min Act: -0.1700

Data Index: 1062096 (Open Web Text)

Max Activating Token Index: 268

Text #3

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7307. Min Act: -0.1700

Data Index: 7702078 (Open Web Text)

Max Activating Token Index: 981

Text #4

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7028. Min Act: -0.1700

Data Index: 2935264 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.7224. Min Act: -0.1700

Data Index: 3069806 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6761. Min Act: -0.1700

Data Index: 6793804 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6869. Min Act: -0.1700

Data Index: 6315665 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6625. Min Act: -0.1700

Data Index: 5524403 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6329. Min Act: -0.1700

Data Index: 4620551 (Open Web Text)

Max Activating Token Index: 90

Text #10

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6484. Min Act: -0.1700

Data Index: 3948878 (Open Web Text)

Max Activating Token Index: 635

Text #11

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6394. Min Act: -0.1700

Data Index: 6803403 (Open Web Text)

Max Activating Token Index: 121

Text #12

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6562. Min Act: -0.1700

Data Index: 206735 (Open Web Text)

Max Activating Token Index: 90

Text #13

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6391. Min Act: -0.1700

Data Index: 3283548 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6352. Min Act: -0.1700

Data Index: 4241298 (Open Web Text)

Max Activating Token Index: 168

Text #15

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6197. Min Act: -0.1700

Data Index: 1208340 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.5953. Min Act: -0.1700

Data Index: 3553073 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6098. Min Act: -0.1700

Data Index: 1347490 (Open Web Text)

Max Activating Token Index: 544

Text #18

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6043. Min Act: -0.1700

Data Index: 8411306 (Open Web Text)

Max Activating Token Index: 319

Text #19

Max Range: 4.8775. Min Range: -4.8775

Max Act: 4.6258. Min Act: -0.1700

Data Index: 1653157 (Open Web Text)

Max Activating Token Index: 296