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

Dataset: Open Web Text

Neuron 685 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: 4.6474. Min Range: -4.6474

Max Act: 4.6474. Min Act: -0.1700

Data Index: 7303729 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.3145. Min Act: -0.1700

Data Index: 5864219 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.1569. Min Act: -0.1700

Data Index: 956519 (Open Web Text)

Max Activating Token Index: 114

Text #3

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.1839. Min Act: -0.1700

Data Index: 2398999 (Open Web Text)

Max Activating Token Index: 159

Text #4

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.1237. Min Act: -0.1700

Data Index: 2061899 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.1307. Min Act: -0.1700

Data Index: 4911943 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.1482. Min Act: -0.1700

Data Index: 6145310 (Open Web Text)

Max Activating Token Index: 499

Text #7

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0739. Min Act: -0.1700

Data Index: 6165839 (Open Web Text)

Max Activating Token Index: 860

Text #8

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0724. Min Act: -0.1700

Data Index: 6833227 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0925. Min Act: -0.1700

Data Index: 8631574 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0169. Min Act: -0.1700

Data Index: 115336 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0304. Min Act: -0.1700

Data Index: 3263802 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0184. Min Act: -0.1700

Data Index: 2718782 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 4.6474. Min Range: -4.6474

Max Act: 4.0265. Min Act: -0.1700

Data Index: 602112 (Open Web Text)

Max Activating Token Index: 950

Text #14

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9376. Min Act: -0.1700

Data Index: 8699399 (Open Web Text)

Max Activating Token Index: 756

Text #15

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9445. Min Act: -0.1700

Data Index: 5014525 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9385. Min Act: -0.1700

Data Index: 8016724 (Open Web Text)

Max Activating Token Index: 478

Text #17

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9061. Min Act: -0.1700

Data Index: 5319035 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9127. Min Act: -0.1700

Data Index: 1270991 (Open Web Text)

Max Activating Token Index: 232

Text #19

Max Range: 4.6474. Min Range: -4.6474

Max Act: 3.9301. Min Act: -0.1700

Data Index: 894050 (Open Web Text)

Max Activating Token Index: 192