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

Dataset: Open Web Text

Neuron 127 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: 1.4987. Min Range: -1.4987

Max Act: 1.4987. Min Act: -0.1700

Data Index: 5279223 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4816. Min Act: -0.1699

Data Index: 3016869 (Open Web Text)

Max Activating Token Index: 1018

Text #2

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4852. Min Act: -0.1700

Data Index: 1680231 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4626. Min Act: -0.1700

Data Index: 6236847 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4259. Min Act: -0.1696

Data Index: 5192152 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4032. Min Act: -0.1666

Data Index: 8381724 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.4059. Min Act: -0.1580

Data Index: 5324513 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3884. Min Act: -0.1699

Data Index: 3016870 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3953. Min Act: -0.1694

Data Index: 3401208 (Open Web Text)

Max Activating Token Index: 347

Text #9

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3845. Min Act: -0.1700

Data Index: 16519 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3891. Min Act: -0.1698

Data Index: 7136643 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3812. Min Act: -0.1685

Data Index: 7267951 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3799. Min Act: -0.1699

Data Index: 5279224 (Open Web Text)

Max Activating Token Index: 615

Text #13

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3826. Min Act: -0.1700

Data Index: 6900886 (Open Web Text)

Max Activating Token Index: 271

Text #14

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3792. Min Act: -0.1697

Data Index: 2936295 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3850. Min Act: -0.1697

Data Index: 5866539 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3766. Min Act: -0.1691

Data Index: 16517 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3642. Min Act: -0.1699

Data Index: 4720215 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3684. Min Act: -0.1693

Data Index: 5279222 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 1.4987. Min Range: -1.4987

Max Act: 1.3660. Min Act: -0.1694

Data Index: 1311431 (Open Web Text)

Max Activating Token Index: 949