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

Dataset: Open Web Text

Neuron 1314 in Layer 3

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: 3.1154. Min Range: -3.1154

Max Act: 3.1154. Min Act: -0.1700

Data Index: 2548970 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 3.1154. Min Range: -3.1154

Max Act: 3.0959. Min Act: -0.1700

Data Index: 4114826 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 3.1154. Min Range: -3.1154

Max Act: 3.0454. Min Act: -0.1700

Data Index: 6304256 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.1154. Min Range: -3.1154

Max Act: 3.0417. Min Act: -0.1700

Data Index: 8677970 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9842. Min Act: -0.1700

Data Index: 5011708 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9702. Min Act: -0.1700

Data Index: 4552518 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9589. Min Act: -0.1700

Data Index: 5348003 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9364. Min Act: -0.1700

Data Index: 6308851 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9465. Min Act: -0.1700

Data Index: 2625433 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9543. Min Act: -0.1700

Data Index: 6698496 (Open Web Text)

Max Activating Token Index: 528

Text #10

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9236. Min Act: -0.1700

Data Index: 5990366 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9269. Min Act: -0.1700

Data Index: 1402511 (Open Web Text)

Max Activating Token Index: 703

Text #12

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9024. Min Act: -0.1700

Data Index: 3119561 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9298. Min Act: -0.1700

Data Index: 1264469 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9435. Min Act: -0.1700

Data Index: 1824281 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9120. Min Act: -0.1700

Data Index: 362410 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9051. Min Act: -0.1700

Data Index: 1959285 (Open Web Text)

Max Activating Token Index: 833

Text #17

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9107. Min Act: -0.1700

Data Index: 4500122 (Open Web Text)

Max Activating Token Index: 74

Text #18

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.8958. Min Act: -0.1700

Data Index: 547124 (Open Web Text)

Max Activating Token Index: 362

Text #19

Max Range: 3.1154. Min Range: -3.1154

Max Act: 2.9065. Min Act: -0.1700

Data Index: 666348 (Open Web Text)

Max Activating Token Index: 748