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

Dataset: Open Web Text

Neuron 2518 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: 3.6495. Min Range: -3.6495

Max Act: 3.6363. Min Act: -0.1700

Data Index: 7538810 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.6495. Min Act: -0.1700

Data Index: 6380760 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.6237. Min Act: -0.1700

Data Index: 2018828 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.6257. Min Act: -0.1700

Data Index: 2660497 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.6204. Min Act: -0.1700

Data Index: 6017949 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5820. Min Act: -0.1700

Data Index: 5608845 (Open Web Text)

Max Activating Token Index: 570

Text #6

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5593. Min Act: -0.1700

Data Index: 8809362 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5667. Min Act: -0.1700

Data Index: 2144923 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5659. Min Act: -0.1700

Data Index: 6133934 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5599. Min Act: -0.1700

Data Index: 8317851 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5639. Min Act: -0.1700

Data Index: 3685821 (Open Web Text)

Max Activating Token Index: 547

Text #11

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5659. Min Act: -0.1700

Data Index: 6816458 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.4982. Min Act: -0.1700

Data Index: 5005076 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5494. Min Act: -0.1700

Data Index: 8380670 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5093. Min Act: -0.1700

Data Index: 3442610 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5289. Min Act: -0.1700

Data Index: 5896861 (Open Web Text)

Max Activating Token Index: 416

Text #16

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5057. Min Act: -0.1700

Data Index: 2074657 (Open Web Text)

Max Activating Token Index: 435

Text #17

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5275. Min Act: -0.1700

Data Index: 4199634 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5183. Min Act: -0.1700

Data Index: 1666704 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 3.6495. Min Range: -3.6495

Max Act: 3.5143. Min Act: -0.1700

Data Index: 2753875 (Open Web Text)

Max Activating Token Index: 565