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

Dataset: Open Web Text

Neuron 245 in Layer 1

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: 2.1024. Min Range: -2.1024

Max Act: 2.1024. Min Act: -0.1700

Data Index: 1906705 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0842. Min Act: -0.1700

Data Index: 8386338 (Open Web Text)

Max Activating Token Index: 785

Text #2

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0500. Min Act: -0.1700

Data Index: 4306042 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0559. Min Act: -0.1700

Data Index: 379368 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0594. Min Act: -0.1700

Data Index: 5808551 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0475. Min Act: -0.1700

Data Index: 1764917 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0373. Min Act: -0.1700

Data Index: 8004734 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0188. Min Act: -0.1700

Data Index: 7782112 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0155. Min Act: -0.1700

Data Index: 247588 (Open Web Text)

Max Activating Token Index: 474

Text #9

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0232. Min Act: -0.1700

Data Index: 4607137 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0092. Min Act: -0.1700

Data Index: 3251183 (Open Web Text)

Max Activating Token Index: 591

Text #11

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0256. Min Act: -0.1700

Data Index: 4373795 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0352. Min Act: -0.1700

Data Index: 3005831 (Open Web Text)

Max Activating Token Index: 329

Text #13

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0188. Min Act: -0.1700

Data Index: 2618338 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.9945. Min Act: -0.1700

Data Index: 4391755 (Open Web Text)

Max Activating Token Index: 100

Text #15

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0188. Min Act: -0.1700

Data Index: 8230503 (Open Web Text)

Max Activating Token Index: 474

Text #16

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0035. Min Act: -0.1700

Data Index: 744768 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.0029. Min Act: -0.1700

Data Index: 5889965 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.9993. Min Act: -0.1700

Data Index: 7916163 (Open Web Text)

Max Activating Token Index: 531

Text #19

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.9952. Min Act: -0.1700

Data Index: 6705177 (Open Web Text)

Max Activating Token Index: 767