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

Dataset: Open Web Text

Neuron 2834 in Layer 2

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: 7.6362. Min Range: -7.6362

Max Act: 7.6362. Min Act: -0.1700

Data Index: 6695873 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 7.6362. Min Range: -7.6362

Max Act: 7.5569. Min Act: -0.1700

Data Index: 5785294 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 7.6362. Min Range: -7.6362

Max Act: 7.3516. Min Act: -0.1700

Data Index: 5511418 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 7.6362. Min Range: -7.6362

Max Act: 7.1834. Min Act: -0.1700

Data Index: 6907426 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 7.6362. Min Range: -7.6362

Max Act: 7.2403. Min Act: -0.1700

Data Index: 2706858 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 7.6362. Min Range: -7.6362

Max Act: 7.0182. Min Act: -0.1700

Data Index: 2182737 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.9196. Min Act: -0.1700

Data Index: 1725416 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.8561. Min Act: -0.1700

Data Index: 8624241 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.8641. Min Act: -0.1700

Data Index: 6621885 (Open Web Text)

Max Activating Token Index: 157

Text #9

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.8368. Min Act: -0.1700

Data Index: 5005807 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.8237. Min Act: -0.1700

Data Index: 923004 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.9003. Min Act: -0.1700

Data Index: 6270912 (Open Web Text)

Max Activating Token Index: 798

Text #12

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.7714. Min Act: -0.1700

Data Index: 4907017 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.6931. Min Act: -0.1700

Data Index: 8113454 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.7303. Min Act: -0.1700

Data Index: 7103244 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.6873. Min Act: -0.1700

Data Index: 2773080 (Open Web Text)

Max Activating Token Index: 108

Text #16

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.5627. Min Act: -0.1700

Data Index: 5660697 (Open Web Text)

Max Activating Token Index: 146

Text #17

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.5961. Min Act: -0.1700

Data Index: 6424919 (Open Web Text)

Max Activating Token Index: 406

Text #18

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.5810. Min Act: -0.1700

Data Index: 5201868 (Open Web Text)

Max Activating Token Index: 481

Text #19

Max Range: 7.6362. Min Range: -7.6362

Max Act: 6.5083. Min Act: -0.1700

Data Index: 7297707 (Open Web Text)

Max Activating Token Index: 645