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

Dataset: Open Web Text

Neuron 1996 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: 4.5880. Min Range: -4.5880

Max Act: 4.5880. Min Act: -0.1700

Data Index: 8396232 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.5329. Min Act: -0.1700

Data Index: 8212807 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.5044. Min Act: -0.1700

Data Index: 4937827 (Open Web Text)

Max Activating Token Index: 912

Text #3

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4710. Min Act: -0.1700

Data Index: 320829 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4616. Min Act: -0.1700

Data Index: 3796229 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4289. Min Act: -0.1700

Data Index: 5594137 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4284. Min Act: -0.1700

Data Index: 8133577 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3779. Min Act: -0.1700

Data Index: 1609850 (Open Web Text)

Max Activating Token Index: 688

Text #8

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3644. Min Act: -0.1700

Data Index: 7882210 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3128. Min Act: -0.1700

Data Index: 7690809 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3277. Min Act: -0.1700

Data Index: 2658886 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2848. Min Act: -0.1700

Data Index: 276889 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2790. Min Act: -0.1700

Data Index: 3694828 (Open Web Text)

Max Activating Token Index: 92

Text #13

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3307. Min Act: -0.1700

Data Index: 315779 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2992. Min Act: -0.1700

Data Index: 4937826 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3137. Min Act: -0.1700

Data Index: 7476917 (Open Web Text)

Max Activating Token Index: 114

Text #16

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2736. Min Act: -0.1700

Data Index: 3678487 (Open Web Text)

Max Activating Token Index: 971

Text #17

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2460. Min Act: -0.1700

Data Index: 8300158 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2796. Min Act: -0.1700

Data Index: 8218930 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.2531. Min Act: -0.1700

Data Index: 3714850 (Open Web Text)

Max Activating Token Index: 99