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

Dataset: Open Web Text

Neuron 796 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: 4.9880. Min Range: -4.9880

Max Act: 4.9880. Min Act: -0.1700

Data Index: 7247377 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7747. Min Act: -0.1700

Data Index: 2037235 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7156. Min Act: -0.1700

Data Index: 374076 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7397. Min Act: -0.1700

Data Index: 6302237 (Open Web Text)

Max Activating Token Index: 436

Text #4

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7473. Min Act: -0.1700

Data Index: 5924660 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7373. Min Act: -0.1700

Data Index: 848072 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6988. Min Act: -0.1700

Data Index: 2454564 (Open Web Text)

Max Activating Token Index: 164

Text #7

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.7009. Min Act: -0.1700

Data Index: 2345512 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6782. Min Act: -0.1700

Data Index: 2127969 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6963. Min Act: -0.1700

Data Index: 368141 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6760. Min Act: -0.1700

Data Index: 7994573 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6898. Min Act: -0.1700

Data Index: 1864154 (Open Web Text)

Max Activating Token Index: 599

Text #12

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6806. Min Act: -0.1700

Data Index: 5398661 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6406. Min Act: -0.1700

Data Index: 3038794 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6411. Min Act: -0.1700

Data Index: 2986373 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6230. Min Act: -0.1700

Data Index: 5921088 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6375. Min Act: -0.1700

Data Index: 6404975 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6472. Min Act: -0.1700

Data Index: 1318618 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6636. Min Act: -0.1700

Data Index: 6595411 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.9880. Min Range: -4.9880

Max Act: 4.6128. Min Act: -0.1700

Data Index: 5059003 (Open Web Text)

Max Activating Token Index: 953