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

Dataset: Open Web Text

Neuron 217 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: 5.1505. Min Range: -5.1505

Max Act: 5.1325. Min Act: -0.1700

Data Index: 1489825 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 5.1505. Min Range: -5.1505

Max Act: 5.1505. Min Act: -0.1700

Data Index: 4199113 (Open Web Text)

Max Activating Token Index: 583

Text #2

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.9902. Min Act: -0.1700

Data Index: 6108742 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.9201. Min Act: -0.1700

Data Index: 5217928 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.9506. Min Act: -0.1700

Data Index: 319727 (Open Web Text)

Max Activating Token Index: 153

Text #5

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.9074. Min Act: -0.1700

Data Index: 6216001 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8668. Min Act: -0.1700

Data Index: 6925551 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8548. Min Act: -0.1700

Data Index: 6301130 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8665. Min Act: -0.1700

Data Index: 6536633 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8487. Min Act: -0.1700

Data Index: 4778904 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8824. Min Act: -0.1700

Data Index: 2033971 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8669. Min Act: -0.1700

Data Index: 1401020 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8951. Min Act: -0.1700

Data Index: 7678336 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.7680. Min Act: -0.1700

Data Index: 2114290 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8475. Min Act: -0.1700

Data Index: 3500824 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8142. Min Act: -0.1700

Data Index: 3852513 (Open Web Text)

Max Activating Token Index: 690

Text #16

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8671. Min Act: -0.1700

Data Index: 236638 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8333. Min Act: -0.1700

Data Index: 3456749 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8438. Min Act: -0.1700

Data Index: 8729047 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 5.1505. Min Range: -5.1505

Max Act: 4.8891. Min Act: -0.1700

Data Index: 5993369 (Open Web Text)

Max Activating Token Index: 966