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

Dataset: Open Web Text

Neuron 2201 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: 5.8866. Min Range: -5.8866

Max Act: 5.8866. Min Act: -0.1700

Data Index: 1258050 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.7904. Min Act: -0.1700

Data Index: 1144314 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.6613. Min Act: -0.1700

Data Index: 6645628 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.5991. Min Act: -0.1700

Data Index: 2578791 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.6011. Min Act: -0.1700

Data Index: 6745095 (Open Web Text)

Max Activating Token Index: 97

Text #5

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.5261. Min Act: -0.1700

Data Index: 5422823 (Open Web Text)

Max Activating Token Index: 712

Text #6

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4952. Min Act: -0.1700

Data Index: 3949703 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.5032. Min Act: -0.1700

Data Index: 4641609 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4691. Min Act: -0.1700

Data Index: 8178152 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.5018. Min Act: -0.1700

Data Index: 8588286 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4459. Min Act: -0.1700

Data Index: 391536 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4013. Min Act: -0.1700

Data Index: 5138931 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4430. Min Act: -0.1700

Data Index: 4195288 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4151. Min Act: -0.1700

Data Index: 7849200 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.3866. Min Act: -0.1700

Data Index: 672373 (Open Web Text)

Max Activating Token Index: 157

Text #15

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.3591. Min Act: -0.1700

Data Index: 5717226 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4343. Min Act: -0.1700

Data Index: 8439946 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4306. Min Act: -0.1700

Data Index: 973574 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.3854. Min Act: -0.1700

Data Index: 3121472 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 5.8866. Min Range: -5.8866

Max Act: 5.4155. Min Act: -0.1700

Data Index: 3879522 (Open Web Text)

Max Activating Token Index: 636