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

Dataset: Open Web Text

Neuron 702 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: 6.3260. Min Range: -6.3260

Max Act: 6.3260. Min Act: -0.1700

Data Index: 1214670 (Open Web Text)

Max Activating Token Index: 71

Text #1

Max Range: 6.3260. Min Range: -6.3260

Max Act: 6.0116. Min Act: -0.1700

Data Index: 4805263 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.8884. Min Act: -0.1700

Data Index: 330882 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.9070. Min Act: -0.1700

Data Index: 5587610 (Open Web Text)

Max Activating Token Index: 215

Text #4

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.8447. Min Act: -0.1700

Data Index: 2535065 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.8110. Min Act: -0.1700

Data Index: 6132706 (Open Web Text)

Max Activating Token Index: 999

Text #6

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.8519. Min Act: -0.1700

Data Index: 6891220 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.8095. Min Act: -0.1700

Data Index: 8209531 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.7026. Min Act: -0.1700

Data Index: 8343140 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.7032. Min Act: -0.1700

Data Index: 3790651 (Open Web Text)

Max Activating Token Index: 683

Text #10

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.6634. Min Act: -0.1700

Data Index: 5095573 (Open Web Text)

Max Activating Token Index: 692

Text #11

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.6446. Min Act: -0.1700

Data Index: 385960 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.6935. Min Act: -0.1700

Data Index: 5701080 (Open Web Text)

Max Activating Token Index: 415

Text #13

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.6659. Min Act: -0.1700

Data Index: 2536905 (Open Web Text)

Max Activating Token Index: 428

Text #14

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.6019. Min Act: -0.1700

Data Index: 1427295 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.5557. Min Act: -0.1700

Data Index: 727342 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.5750. Min Act: -0.1700

Data Index: 350642 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.5214. Min Act: -0.1700

Data Index: 5811330 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.5371. Min Act: -0.1700

Data Index: 406306 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 6.3260. Min Range: -6.3260

Max Act: 5.5282. Min Act: -0.1700

Data Index: 8111922 (Open Web Text)

Max Activating Token Index: 393