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

Dataset: Open Web Text

Neuron 2303 in Layer 3

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: 4.6907. Min Range: -4.6907

Max Act: 4.6907. Min Act: -0.1700

Data Index: 6442107 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.5665. Min Act: -0.1700

Data Index: 868565 (Open Web Text)

Max Activating Token Index: 466

Text #2

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.5510. Min Act: -0.1700

Data Index: 7349994 (Open Web Text)

Max Activating Token Index: 329

Text #3

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3754. Min Act: -0.1700

Data Index: 1336701 (Open Web Text)

Max Activating Token Index: 109

Text #4

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3797. Min Act: -0.1700

Data Index: 6564402 (Open Web Text)

Max Activating Token Index: 546

Text #5

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3648. Min Act: -0.1700

Data Index: 3510930 (Open Web Text)

Max Activating Token Index: 859

Text #6

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3682. Min Act: -0.1700

Data Index: 4788180 (Open Web Text)

Max Activating Token Index: 810

Text #7

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3670. Min Act: -0.1700

Data Index: 4323579 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3752. Min Act: -0.1700

Data Index: 3637812 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3576. Min Act: -0.1700

Data Index: 169311 (Open Web Text)

Max Activating Token Index: 862

Text #10

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3149. Min Act: -0.1700

Data Index: 4231709 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.2860. Min Act: -0.1700

Data Index: 819964 (Open Web Text)

Max Activating Token Index: 904

Text #12

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3182. Min Act: -0.1700

Data Index: 3813550 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3675. Min Act: -0.1700

Data Index: 7960581 (Open Web Text)

Max Activating Token Index: 448

Text #14

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3626. Min Act: -0.1700

Data Index: 1738296 (Open Web Text)

Max Activating Token Index: 491

Text #15

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3137. Min Act: -0.1700

Data Index: 1443560 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3503. Min Act: -0.1700

Data Index: 6870888 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3243. Min Act: -0.1700

Data Index: 5787419 (Open Web Text)

Max Activating Token Index: 285

Text #18

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.2867. Min Act: -0.1700

Data Index: 2518799 (Open Web Text)

Max Activating Token Index: 1008

Text #19

Max Range: 4.6907. Min Range: -4.6907

Max Act: 4.3171. Min Act: -0.1700

Data Index: 5593918 (Open Web Text)

Max Activating Token Index: 791