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

Dataset: Open Web Text

Neuron 71 in Layer 6

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: 5.7891. Min Range: -5.7891

Max Act: 5.7891. Min Act: -0.1700

Data Index: 5980733 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.7067. Min Act: -0.1700

Data Index: 6366048 (Open Web Text)

Max Activating Token Index: 707

Text #2

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.6494. Min Act: -0.1700

Data Index: 1963835 (Open Web Text)

Max Activating Token Index: 305

Text #3

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.6043. Min Act: -0.1700

Data Index: 957183 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.6140. Min Act: -0.1700

Data Index: 8064035 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5846. Min Act: -0.1700

Data Index: 5158777 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5761. Min Act: -0.1700

Data Index: 6854642 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5484. Min Act: -0.1700

Data Index: 2460865 (Open Web Text)

Max Activating Token Index: 813

Text #8

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.6108. Min Act: -0.1700

Data Index: 7164076 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5557. Min Act: -0.1700

Data Index: 6255220 (Open Web Text)

Max Activating Token Index: 348

Text #10

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5505. Min Act: -0.1700

Data Index: 2171799 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5447. Min Act: -0.1700

Data Index: 1800614 (Open Web Text)

Max Activating Token Index: 692

Text #12

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5302. Min Act: -0.1700

Data Index: 1129091 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4976. Min Act: -0.1700

Data Index: 4467807 (Open Web Text)

Max Activating Token Index: 82

Text #14

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.5225. Min Act: -0.1700

Data Index: 4102597 (Open Web Text)

Max Activating Token Index: 450

Text #15

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4440. Min Act: -0.1700

Data Index: 3427369 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4942. Min Act: -0.1700

Data Index: 5543354 (Open Web Text)

Max Activating Token Index: 1011

Text #17

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4685. Min Act: -0.1700

Data Index: 3107575 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4639. Min Act: -0.1700

Data Index: 1382178 (Open Web Text)

Max Activating Token Index: 884

Text #19

Max Range: 5.7891. Min Range: -5.7891

Max Act: 5.4852. Min Act: -0.1700

Data Index: 1578954 (Open Web Text)

Max Activating Token Index: 62