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

Dataset: Open Web Text

Neuron 382 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: 0.6773. Min Range: -0.6773

Max Act: 0.6773. Min Act: -0.1700

Data Index: 4799920 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6355. Min Act: -0.1700

Data Index: 5844881 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6065. Min Act: -0.1699

Data Index: 3802531 (Open Web Text)

Max Activating Token Index: 697

Text #3

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5993. Min Act: -0.1700

Data Index: 1651581 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5846. Min Act: -0.1700

Data Index: 6789047 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5747. Min Act: -0.1700

Data Index: 4020846 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5742. Min Act: -0.1700

Data Index: 7319886 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5577. Min Act: -0.1700

Data Index: 3485494 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5543. Min Act: -0.1700

Data Index: 5210361 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5494. Min Act: -0.1700

Data Index: 310596 (Open Web Text)

Max Activating Token Index: 687

Text #10

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5603. Min Act: -0.1700

Data Index: 5388072 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5478. Min Act: -0.1700

Data Index: 4890417 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5530. Min Act: -0.1700

Data Index: 2859845 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5562. Min Act: -0.1700

Data Index: 7108452 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5542. Min Act: -0.1700

Data Index: 672464 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5585. Min Act: -0.1700

Data Index: 1093178 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5539. Min Act: -0.1700

Data Index: 7802795 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5465. Min Act: -0.1700

Data Index: 6571000 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5396. Min Act: -0.1700

Data Index: 6539740 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5444. Min Act: -0.1700

Data Index: 4026495 (Open Web Text)

Max Activating Token Index: 683