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

Dataset: Open Web Text

Neuron 1772 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: 1.7892. Min Range: -1.7892

Max Act: 1.7892. Min Act: -0.1700

Data Index: 5637597 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7839. Min Act: -0.1700

Data Index: 1188474 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7571. Min Act: -0.1700

Data Index: 8178109 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7663. Min Act: -0.1700

Data Index: 2253672 (Open Web Text)

Max Activating Token Index: 197

Text #4

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7522. Min Act: -0.1700

Data Index: 2552726 (Open Web Text)

Max Activating Token Index: 975

Text #5

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7642. Min Act: -0.1700

Data Index: 5331797 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7524. Min Act: -0.1700

Data Index: 4948288 (Open Web Text)

Max Activating Token Index: 324

Text #7

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7595. Min Act: -0.1700

Data Index: 7086979 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7516. Min Act: -0.1700

Data Index: 3334672 (Open Web Text)

Max Activating Token Index: 434

Text #9

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7478. Min Act: -0.1700

Data Index: 2253674 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7449. Min Act: -0.1700

Data Index: 5169054 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7390. Min Act: -0.1700

Data Index: 4841825 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7330. Min Act: -0.1700

Data Index: 6025064 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7300. Min Act: -0.1700

Data Index: 8683274 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7236. Min Act: -0.1700

Data Index: 5509710 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7155. Min Act: -0.1700

Data Index: 3375013 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7164. Min Act: -0.1699

Data Index: 1214717 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7174. Min Act: -0.1700

Data Index: 3877397 (Open Web Text)

Max Activating Token Index: 147

Text #18

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7276. Min Act: -0.1700

Data Index: 850298 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.7892. Min Range: -1.7892

Max Act: 1.7054. Min Act: -0.1700

Data Index: 4807891 (Open Web Text)

Max Activating Token Index: 513