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

Dataset: Open Web Text

Neuron 3 in Layer 1

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: 1.6305. Min Range: -1.6305

Max Act: 1.6305. Min Act: -0.1700

Data Index: 5842410 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5775. Min Act: -0.1700

Data Index: 5317299 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5477. Min Act: -0.1700

Data Index: 7383921 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5416. Min Act: -0.1700

Data Index: 7194161 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5295. Min Act: -0.1700

Data Index: 6928980 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5235. Min Act: -0.1700

Data Index: 5423619 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5303. Min Act: -0.1700

Data Index: 2071415 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5237. Min Act: -0.1700

Data Index: 4572839 (Open Web Text)

Max Activating Token Index: 486

Text #8

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5211. Min Act: -0.1700

Data Index: 2595373 (Open Web Text)

Max Activating Token Index: 424

Text #9

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5140. Min Act: -0.1700

Data Index: 4105603 (Open Web Text)

Max Activating Token Index: 381

Text #10

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5124. Min Act: -0.1700

Data Index: 5453273 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5079. Min Act: -0.1700

Data Index: 6811495 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5114. Min Act: -0.1700

Data Index: 1278403 (Open Web Text)

Max Activating Token Index: 366

Text #13

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5111. Min Act: -0.1700

Data Index: 3274473 (Open Web Text)

Max Activating Token Index: 687

Text #14

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5124. Min Act: -0.1700

Data Index: 4701605 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5078. Min Act: -0.1700

Data Index: 1360609 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5069. Min Act: -0.1700

Data Index: 3808098 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.4957. Min Act: -0.1700

Data Index: 2604349 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.5024. Min Act: -0.1700

Data Index: 787461 (Open Web Text)

Max Activating Token Index: 616

Text #19

Max Range: 1.6305. Min Range: -1.6305

Max Act: 1.4930. Min Act: -0.1700

Data Index: 3956223 (Open Web Text)

Max Activating Token Index: 381