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

Dataset: Open Web Text

Neuron 1152 in Layer 4

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: 1.9646. Min Range: -1.9646

Max Act: 1.9646. Min Act: -0.1700

Data Index: 4474237 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9149. Min Act: -0.1700

Data Index: 2355091 (Open Web Text)

Max Activating Token Index: 432

Text #2

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9111. Min Act: -0.1700

Data Index: 3858111 (Open Web Text)

Max Activating Token Index: 660

Text #3

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9139. Min Act: -0.1700

Data Index: 1731460 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9253. Min Act: -0.1700

Data Index: 3176603 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9055. Min Act: -0.1700

Data Index: 7350438 (Open Web Text)

Max Activating Token Index: 322

Text #6

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9016. Min Act: -0.1700

Data Index: 180399 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9043. Min Act: -0.1700

Data Index: 2030946 (Open Web Text)

Max Activating Token Index: 445

Text #8

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9174. Min Act: -0.1700

Data Index: 6924623 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8876. Min Act: -0.1700

Data Index: 9435 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8796. Min Act: -0.1700

Data Index: 4319372 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8876. Min Act: -0.1700

Data Index: 4681939 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8980. Min Act: -0.1700

Data Index: 7215820 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8883. Min Act: -0.1700

Data Index: 7668994 (Open Web Text)

Max Activating Token Index: 576

Text #14

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8995. Min Act: -0.1700

Data Index: 7457438 (Open Web Text)

Max Activating Token Index: 433

Text #15

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8830. Min Act: -0.1700

Data Index: 2745307 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8612. Min Act: -0.1700

Data Index: 8624010 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8741. Min Act: -0.1700

Data Index: 6168167 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8613. Min Act: -0.1700

Data Index: 5972841 (Open Web Text)

Max Activating Token Index: 654

Text #19

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.8678. Min Act: -0.1700

Data Index: 697398 (Open Web Text)

Max Activating Token Index: 983