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

Dataset: Open Web Text

Neuron 2500 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: 3.5854. Min Range: -3.5854

Max Act: 3.4656. Min Act: -0.1700

Data Index: 1537735 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5370. Min Act: -0.1700

Data Index: 2979449 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.5854. Min Act: -0.1700

Data Index: 1141288 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4995. Min Act: -0.1700

Data Index: 4879515 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4673. Min Act: -0.1700

Data Index: 5071716 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.4137. Min Act: -0.1700

Data Index: 8587710 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2675. Min Act: -0.1700

Data Index: 6164745 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2446. Min Act: -0.1700

Data Index: 2198721 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1262756 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2108. Min Act: -0.1700

Data Index: 5617126 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.1806. Min Act: -0.1700

Data Index: 2338558 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.3541. Min Act: -0.1700

Data Index: 5902658 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2009. Min Act: -0.1700

Data Index: 2270003 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2889. Min Act: -0.1700

Data Index: 4588249 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2025. Min Act: -0.1700

Data Index: 1744772 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.1945. Min Act: -0.1700

Data Index: 66420 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2010. Min Act: -0.1700

Data Index: 5228489 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2421. Min Act: -0.1700

Data Index: 8774055 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.2264. Min Act: -0.1700

Data Index: 6808498 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5854. Min Range: -3.5854

Max Act: 3.1845. Min Act: -0.1700

Data Index: 7379873 (Open Web Text)

Max Activating Token Index: 1023