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

Dataset: Open Web Text

Neuron 921 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: 3.0564. Min Range: -3.0564

Max Act: 3.0564. Min Act: -0.1700

Data Index: 6551388 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9555. Min Act: -0.1700

Data Index: 6030405 (Open Web Text)

Max Activating Token Index: 953

Text #2

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9410. Min Act: -0.1700

Data Index: 7997960 (Open Web Text)

Max Activating Token Index: 286

Text #3

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9282. Min Act: -0.1700

Data Index: 4699163 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9130. Min Act: -0.1700

Data Index: 5276872 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9147. Min Act: -0.1700

Data Index: 3035528 (Open Web Text)

Max Activating Token Index: 830

Text #6

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9112. Min Act: -0.1700

Data Index: 8445846 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9093. Min Act: -0.1700

Data Index: 8022323 (Open Web Text)

Max Activating Token Index: 134

Text #8

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.9021. Min Act: -0.1700

Data Index: 6929502 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8786. Min Act: -0.1700

Data Index: 31168 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8949. Min Act: -0.1700

Data Index: 5149066 (Open Web Text)

Max Activating Token Index: 695

Text #11

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8622. Min Act: -0.1700

Data Index: 3666479 (Open Web Text)

Max Activating Token Index: 767

Text #12

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8744. Min Act: -0.1700

Data Index: 3180850 (Open Web Text)

Max Activating Token Index: 289

Text #13

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8714. Min Act: -0.1700

Data Index: 4494813 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8567. Min Act: -0.1700

Data Index: 7481670 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8581. Min Act: -0.1700

Data Index: 3710923 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8474. Min Act: -0.1700

Data Index: 4285529 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8503. Min Act: -0.1700

Data Index: 7560146 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8373. Min Act: -0.1700

Data Index: 4220262 (Open Web Text)

Max Activating Token Index: 271

Text #19

Max Range: 3.0564. Min Range: -3.0564

Max Act: 2.8327. Min Act: -0.1700

Data Index: 7591658 (Open Web Text)

Max Activating Token Index: 162