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

Dataset: Open Web Text

Neuron 1442 in Layer 2

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: 1.6766. Min Range: -1.6766

Max Act: 1.6766. Min Act: -0.1700

Data Index: 6984497 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6286. Min Act: -0.1700

Data Index: 1273207 (Open Web Text)

Max Activating Token Index: 418

Text #2

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6012. Min Act: -0.1700

Data Index: 1348031 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5995. Min Act: -0.1700

Data Index: 6688802 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6108. Min Act: -0.1700

Data Index: 5509962 (Open Web Text)

Max Activating Token Index: 854

Text #5

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5872. Min Act: -0.1700

Data Index: 2999777 (Open Web Text)

Max Activating Token Index: 239

Text #6

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6006. Min Act: -0.1700

Data Index: 7975404 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5907. Min Act: -0.1700

Data Index: 5302296 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.6037. Min Act: -0.1700

Data Index: 5317825 (Open Web Text)

Max Activating Token Index: 421

Text #9

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5806. Min Act: -0.1700

Data Index: 4776230 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5825. Min Act: -0.1700

Data Index: 3793314 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5817. Min Act: -0.1700

Data Index: 2830059 (Open Web Text)

Max Activating Token Index: 334

Text #12

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5857. Min Act: -0.1700

Data Index: 7996029 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5834. Min Act: -0.1700

Data Index: 3611005 (Open Web Text)

Max Activating Token Index: 86

Text #14

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5873. Min Act: -0.1700

Data Index: 3691452 (Open Web Text)

Max Activating Token Index: 590

Text #15

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5754. Min Act: -0.1700

Data Index: 8423167 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5682. Min Act: -0.1698

Data Index: 6683366 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5839. Min Act: -0.1700

Data Index: 3975447 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5603. Min Act: -0.1700

Data Index: 3872370 (Open Web Text)

Max Activating Token Index: 359

Text #19

Max Range: 1.6766. Min Range: -1.6766

Max Act: 1.5552. Min Act: -0.1700

Data Index: 1574789 (Open Web Text)

Max Activating Token Index: 760