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

Dataset: Open Web Text

Neuron 3051 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: 3.1952. Min Range: -3.1952

Max Act: 3.1952. Min Act: -0.1700

Data Index: 6256622 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1651. Min Act: -0.1700

Data Index: 7195662 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1628. Min Act: -0.1700

Data Index: 8464233 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1492. Min Act: -0.1700

Data Index: 3485286 (Open Web Text)

Max Activating Token Index: 893

Text #4

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1462. Min Act: -0.1700

Data Index: 3584767 (Open Web Text)

Max Activating Token Index: 1012

Text #5

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1664. Min Act: -0.1700

Data Index: 4343260 (Open Web Text)

Max Activating Token Index: 650

Text #6

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1137. Min Act: -0.1700

Data Index: 4983897 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1422. Min Act: -0.1700

Data Index: 1450424 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1025. Min Act: -0.1700

Data Index: 8023640 (Open Web Text)

Max Activating Token Index: 151

Text #9

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1292. Min Act: -0.1700

Data Index: 1167313 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0624. Min Act: -0.1700

Data Index: 3805086 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.1011. Min Act: -0.1700

Data Index: 769321 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0887. Min Act: -0.1700

Data Index: 4153021 (Open Web Text)

Max Activating Token Index: 295

Text #13

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0626. Min Act: -0.1700

Data Index: 7928037 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0619. Min Act: -0.1700

Data Index: 1614533 (Open Web Text)

Max Activating Token Index: 414

Text #15

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0757. Min Act: -0.1700

Data Index: 6637083 (Open Web Text)

Max Activating Token Index: 34

Text #16

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0839. Min Act: -0.1700

Data Index: 6304128 (Open Web Text)

Max Activating Token Index: 979

Text #17

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0706. Min Act: -0.1700

Data Index: 286893 (Open Web Text)

Max Activating Token Index: 643

Text #18

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0756. Min Act: -0.1700

Data Index: 638586 (Open Web Text)

Max Activating Token Index: 716

Text #19

Max Range: 3.1952. Min Range: -3.1952

Max Act: 3.0747. Min Act: -0.1700

Data Index: 8395491 (Open Web Text)

Max Activating Token Index: 914