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

Dataset: Open Web Text

Neuron 322 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: 3.8898. Min Range: -3.8898

Max Act: 3.8898. Min Act: -0.1700

Data Index: 6612823 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6746. Min Act: -0.1700

Data Index: 3843751 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6415. Min Act: -0.1700

Data Index: 880253 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6089. Min Act: -0.1700

Data Index: 7919240 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.6091. Min Act: -0.1700

Data Index: 7506802 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5890. Min Act: -0.1700

Data Index: 8130634 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5462. Min Act: -0.1700

Data Index: 2836549 (Open Web Text)

Max Activating Token Index: 565

Text #7

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5462. Min Act: -0.1700

Data Index: 2049725 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5286. Min Act: -0.1700

Data Index: 7500442 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5046. Min Act: -0.1700

Data Index: 3852733 (Open Web Text)

Max Activating Token Index: 382

Text #10

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5097. Min Act: -0.1700

Data Index: 4075873 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5404. Min Act: -0.1700

Data Index: 6116280 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.5286. Min Act: -0.1700

Data Index: 621817 (Open Web Text)

Max Activating Token Index: 706

Text #13

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4937. Min Act: -0.1700

Data Index: 5357323 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4885. Min Act: -0.1700

Data Index: 1620474 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4937. Min Act: -0.1700

Data Index: 4028257 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4935. Min Act: -0.1700

Data Index: 2610084 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4667. Min Act: -0.1700

Data Index: 4061447 (Open Web Text)

Max Activating Token Index: 101

Text #18

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4894. Min Act: -0.1700

Data Index: 3614068 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 3.8898. Min Range: -3.8898

Max Act: 3.4796. Min Act: -0.1700

Data Index: 2438844 (Open Web Text)

Max Activating Token Index: 167