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

Dataset: Open Web Text

Neuron 2963 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: 0.5569. Min Range: -0.5569

Max Act: 0.5569. Min Act: -0.1700

Data Index: 8197126 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5364. Min Act: -0.1700

Data Index: 8129475 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5318. Min Act: -0.1700

Data Index: 4795693 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5347. Min Act: -0.1700

Data Index: 1648513 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5255. Min Act: -0.1700

Data Index: 4689526 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5363. Min Act: -0.1700

Data Index: 989648 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5238. Min Act: -0.1700

Data Index: 6331068 (Open Web Text)

Max Activating Token Index: 412

Text #7

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5248. Min Act: -0.1700

Data Index: 4466915 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5335. Min Act: -0.1700

Data Index: 3756135 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5231. Min Act: -0.1700

Data Index: 6810464 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5209. Min Act: -0.1700

Data Index: 1563396 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5125. Min Act: -0.1700

Data Index: 522893 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5186. Min Act: -0.1700

Data Index: 6851178 (Open Web Text)

Max Activating Token Index: 423

Text #13

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5192. Min Act: -0.1700

Data Index: 1055959 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5122. Min Act: -0.1700

Data Index: 1216957 (Open Web Text)

Max Activating Token Index: 425

Text #15

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5131. Min Act: -0.1700

Data Index: 485491 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5068. Min Act: -0.1700

Data Index: 4185987 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5205. Min Act: -0.1700

Data Index: 842495 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5131. Min Act: -0.1700

Data Index: 1565330 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5231. Min Act: -0.1700

Data Index: 3207516 (Open Web Text)

Max Activating Token Index: 436