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

Dataset: Open Web Text

Neuron 844 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: 3.9138. Min Range: -3.9138

Max Act: 3.8996. Min Act: -0.1700

Data Index: 3999489 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.9138. Min Act: -0.1700

Data Index: 7407375 (Open Web Text)

Max Activating Token Index: 351

Text #2

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8991. Min Act: -0.1700

Data Index: 8635663 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8673. Min Act: -0.1700

Data Index: 4841955 (Open Web Text)

Max Activating Token Index: 275

Text #4

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8566. Min Act: -0.1700

Data Index: 7920292 (Open Web Text)

Max Activating Token Index: 187

Text #5

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8545. Min Act: -0.1700

Data Index: 1266987 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8586. Min Act: -0.1700

Data Index: 6344245 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7844. Min Act: -0.1700

Data Index: 4478642 (Open Web Text)

Max Activating Token Index: 193

Text #8

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8099. Min Act: -0.1700

Data Index: 4023392 (Open Web Text)

Max Activating Token Index: 638

Text #9

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7987. Min Act: -0.1700

Data Index: 8720330 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7839. Min Act: -0.1700

Data Index: 2936183 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.8212. Min Act: -0.1700

Data Index: 1537261 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7703. Min Act: -0.1700

Data Index: 470910 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7745. Min Act: -0.1700

Data Index: 6664166 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7909. Min Act: -0.1700

Data Index: 2346498 (Open Web Text)

Max Activating Token Index: 303

Text #15

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7946. Min Act: -0.1700

Data Index: 8350364 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7770. Min Act: -0.1700

Data Index: 7765637 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7628. Min Act: -0.1700

Data Index: 109400 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.6808. Min Act: -0.1700

Data Index: 7381049 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 3.9138. Min Range: -3.9138

Max Act: 3.7770. Min Act: -0.1700

Data Index: 2217531 (Open Web Text)

Max Activating Token Index: 146