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

Dataset: Open Web Text

Neuron 181 in Layer 6

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: 4.4470. Min Range: -4.4470

Max Act: 4.4470. Min Act: -0.1700

Data Index: 4571336 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2906. Min Act: -0.1700

Data Index: 1174646 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2545. Min Act: -0.1700

Data Index: 2800819 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2431. Min Act: -0.1700

Data Index: 1944605 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2625. Min Act: -0.1700

Data Index: 4108978 (Open Web Text)

Max Activating Token Index: 747

Text #5

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2518. Min Act: -0.1700

Data Index: 7261424 (Open Web Text)

Max Activating Token Index: 496

Text #6

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2530. Min Act: -0.1700

Data Index: 6231210 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.2038. Min Act: -0.1700

Data Index: 824527 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1937. Min Act: -0.1700

Data Index: 1117844 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1586. Min Act: -0.1700

Data Index: 1633798 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1753. Min Act: -0.1700

Data Index: 3873093 (Open Web Text)

Max Activating Token Index: 894

Text #11

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1688. Min Act: -0.1700

Data Index: 3458062 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1333. Min Act: -0.1700

Data Index: 6668688 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1334. Min Act: -0.1700

Data Index: 920760 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.0923. Min Act: -0.1700

Data Index: 658805 (Open Web Text)

Max Activating Token Index: 950

Text #15

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.1015. Min Act: -0.1700

Data Index: 2300209 (Open Web Text)

Max Activating Token Index: 486

Text #16

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.0810. Min Act: -0.1700

Data Index: 7094064 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.0628. Min Act: -0.1700

Data Index: 1169628 (Open Web Text)

Max Activating Token Index: 255

Text #18

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.0860. Min Act: -0.1700

Data Index: 858083 (Open Web Text)

Max Activating Token Index: 930

Text #19

Max Range: 4.4470. Min Range: -4.4470

Max Act: 4.0749. Min Act: -0.1700

Data Index: 2954305 (Open Web Text)

Max Activating Token Index: 334