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

Dataset: Open Web Text

Neuron 2930 in Layer 4

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: 3.6002. Min Range: -3.6002

Max Act: 3.5981. Min Act: -0.1700

Data Index: 7400444 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.6002. Min Act: -0.1700

Data Index: 8202036 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.5765. Min Act: -0.1700

Data Index: 6065792 (Open Web Text)

Max Activating Token Index: 302

Text #3

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4976. Min Act: -0.1700

Data Index: 144372 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.5233. Min Act: -0.1700

Data Index: 1188574 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.5101. Min Act: -0.1700

Data Index: 2616715 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1870077 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4542. Min Act: -0.1700

Data Index: 5322893 (Open Web Text)

Max Activating Token Index: 851

Text #8

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.5059. Min Act: -0.1700

Data Index: 5786012 (Open Web Text)

Max Activating Token Index: 996

Text #9

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1495860 (Open Web Text)

Max Activating Token Index: 776

Text #10

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4552. Min Act: -0.1700

Data Index: 3507060 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4656. Min Act: -0.1700

Data Index: 6525775 (Open Web Text)

Max Activating Token Index: 488

Text #12

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4734. Min Act: -0.1700

Data Index: 2680406 (Open Web Text)

Max Activating Token Index: 770

Text #13

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.5208. Min Act: -0.1700

Data Index: 4121273 (Open Web Text)

Max Activating Token Index: 780

Text #14

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4572. Min Act: -0.1700

Data Index: 6218460 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4515. Min Act: -0.1700

Data Index: 8001292 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4595. Min Act: -0.1700

Data Index: 2182877 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4200. Min Act: -0.1700

Data Index: 8052174 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4244. Min Act: -0.1700

Data Index: 1263703 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 3.6002. Min Range: -3.6002

Max Act: 3.4523. Min Act: -0.1700

Data Index: 6101635 (Open Web Text)

Max Activating Token Index: 485