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

Dataset: Open Web Text

Neuron 2897 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: 2.2270. Min Range: -2.2270

Max Act: 2.2270. Min Act: -0.1700

Data Index: 8589858 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1807. Min Act: -0.1700

Data Index: 6586366 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1697. Min Act: -0.1700

Data Index: 6954288 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1587. Min Act: -0.1700

Data Index: 4656307 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1582. Min Act: -0.1700

Data Index: 7931964 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1580. Min Act: -0.1700

Data Index: 7663587 (Open Web Text)

Max Activating Token Index: 600

Text #6

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1432. Min Act: -0.1700

Data Index: 2211172 (Open Web Text)

Max Activating Token Index: 709

Text #7

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1300. Min Act: -0.1700

Data Index: 1004912 (Open Web Text)

Max Activating Token Index: 52

Text #8

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1360. Min Act: -0.1700

Data Index: 1722703 (Open Web Text)

Max Activating Token Index: 566

Text #9

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1458. Min Act: -0.1700

Data Index: 7736662 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1530. Min Act: -0.1700

Data Index: 3938470 (Open Web Text)

Max Activating Token Index: 265

Text #11

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1134. Min Act: -0.1700

Data Index: 2543501 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1145. Min Act: -0.1700

Data Index: 1206310 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1147. Min Act: -0.1700

Data Index: 2543499 (Open Web Text)

Max Activating Token Index: 101

Text #14

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1216. Min Act: -0.1700

Data Index: 578986 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.0997. Min Act: -0.1700

Data Index: 6316107 (Open Web Text)

Max Activating Token Index: 814

Text #16

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1171. Min Act: -0.1700

Data Index: 6860534 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1003. Min Act: -0.1700

Data Index: 4246859 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.1060. Min Act: -0.1700

Data Index: 6602644 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 2.2270. Min Range: -2.2270

Max Act: 2.0848. Min Act: -0.1700

Data Index: 6054712 (Open Web Text)

Max Activating Token Index: 668