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

Dataset: Open Web Text

Neuron 299 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: 3.6363. Min Range: -3.6363

Max Act: 3.6363. Min Act: -0.1700

Data Index: 6801977 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.5164. Min Act: -0.1700

Data Index: 609404 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4564. Min Act: -0.1700

Data Index: 8094568 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4569. Min Act: -0.1700

Data Index: 5723404 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4229. Min Act: -0.1700

Data Index: 3901658 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4122. Min Act: -0.1700

Data Index: 1934161 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4126. Min Act: -0.1700

Data Index: 2628054 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 507891 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4080. Min Act: -0.1700

Data Index: 8242698 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 3440651 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 7535352 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 2116867 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 7324009 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 6312483 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 3687296 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.4138. Min Act: -0.1700

Data Index: 5850910 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.3983. Min Act: -0.1700

Data Index: 7473924 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.3852. Min Act: -0.1700

Data Index: 6008798 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.3905. Min Act: -0.1700

Data Index: 1155065 (Open Web Text)

Max Activating Token Index: 738

Text #19

Max Range: 3.6363. Min Range: -3.6363

Max Act: 3.3870. Min Act: -0.1700

Data Index: 827231 (Open Web Text)

Max Activating Token Index: 41