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

Dataset: Open Web Text

Neuron 399 in Layer 5

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: 6.2004. Min Range: -6.2004

Max Act: 6.2004. Min Act: -0.1700

Data Index: 1034963 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.9519. Min Act: -0.1700

Data Index: 3421396 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.9229. Min Act: -0.1700

Data Index: 1217066 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.8867. Min Act: -0.1700

Data Index: 4534143 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.8520. Min Act: -0.1700

Data Index: 5860508 (Open Web Text)

Max Activating Token Index: 693

Text #5

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.7797. Min Act: -0.1700

Data Index: 5028612 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6943. Min Act: -0.1700

Data Index: 4126135 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6733. Min Act: -0.1700

Data Index: 91413 (Open Web Text)

Max Activating Token Index: 94

Text #8

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6596. Min Act: -0.1700

Data Index: 8552309 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6410. Min Act: -0.1700

Data Index: 2326259 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6416. Min Act: -0.1700

Data Index: 7312456 (Open Web Text)

Max Activating Token Index: 859

Text #11

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6936. Min Act: -0.1700

Data Index: 686610 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6499. Min Act: -0.1700

Data Index: 6785548 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5859. Min Act: -0.1700

Data Index: 8252013 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6184. Min Act: -0.1700

Data Index: 7811026 (Open Web Text)

Max Activating Token Index: 223

Text #15

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6193. Min Act: -0.1700

Data Index: 8792234 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5782. Min Act: -0.1700

Data Index: 8468527 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5946. Min Act: -0.1700

Data Index: 3903172 (Open Web Text)

Max Activating Token Index: 728

Text #18

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.6194. Min Act: -0.1700

Data Index: 497836 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 6.2004. Min Range: -6.2004

Max Act: 5.5863. Min Act: -0.1700

Data Index: 6739263 (Open Web Text)

Max Activating Token Index: 403