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

Dataset: Open Web Text

Neuron 50 in Layer 4

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: 4.1707. Min Range: -4.1707

Max Act: 4.1707. Min Act: -0.1700

Data Index: 5264951 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.1081. Min Act: -0.1700

Data Index: 969058 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0671. Min Act: -0.1700

Data Index: 5288440 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0867. Min Act: -0.1700

Data Index: 7100071 (Open Web Text)

Max Activating Token Index: 350

Text #4

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0609. Min Act: -0.1700

Data Index: 2473193 (Open Web Text)

Max Activating Token Index: 376

Text #5

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0947. Min Act: -0.1700

Data Index: 3917620 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0681. Min Act: -0.1700

Data Index: 2723647 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0605. Min Act: -0.1700

Data Index: 4074139 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0434. Min Act: -0.1700

Data Index: 7527200 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0074. Min Act: -0.1700

Data Index: 750884 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9770. Min Act: -0.1700

Data Index: 6069156 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9981. Min Act: -0.1700

Data Index: 1372494 (Open Web Text)

Max Activating Token Index: 933

Text #12

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1478310 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9935. Min Act: -0.1700

Data Index: 693974 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9876. Min Act: -0.1700

Data Index: 4439243 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0083. Min Act: -0.1700

Data Index: 4651274 (Open Web Text)

Max Activating Token Index: 181

Text #16

Max Range: 4.1707. Min Range: -4.1707

Max Act: 4.0148. Min Act: -0.1700

Data Index: 3531676 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9712. Min Act: -0.1700

Data Index: 6307367 (Open Web Text)

Max Activating Token Index: 916

Text #18

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9502. Min Act: -0.1700

Data Index: 5705230 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 4.1707. Min Range: -4.1707

Max Act: 3.9704. Min Act: -0.1700

Data Index: 4502798 (Open Web Text)

Max Activating Token Index: 604