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

Dataset: Open Web Text

Neuron 1776 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: 4.1687. Min Range: -4.1687

Max Act: 4.1687. Min Act: -0.1700

Data Index: 7797702 (Open Web Text)

Max Activating Token Index: 173

Text #1

Max Range: 4.1687. Min Range: -4.1687

Max Act: 4.0649. Min Act: -0.1700

Data Index: 2847074 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 4.1687. Min Range: -4.1687

Max Act: 4.0733. Min Act: -0.1700

Data Index: 7632580 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 4.1687. Min Range: -4.1687

Max Act: 4.0131. Min Act: -0.1700

Data Index: 7978919 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.9802. Min Act: -0.1700

Data Index: 4172100 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.9392. Min Act: -0.1700

Data Index: 5378933 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.9132. Min Act: -0.1700

Data Index: 8529931 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.9103. Min Act: -0.1700

Data Index: 3214366 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.9131. Min Act: -0.1700

Data Index: 5303158 (Open Web Text)

Max Activating Token Index: 367

Text #9

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8935. Min Act: -0.1700

Data Index: 3558391 (Open Web Text)

Max Activating Token Index: 606

Text #10

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8829. Min Act: -0.1700

Data Index: 5275265 (Open Web Text)

Max Activating Token Index: 265

Text #11

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8187. Min Act: -0.1700

Data Index: 6613307 (Open Web Text)

Max Activating Token Index: 892

Text #12

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8437. Min Act: -0.1700

Data Index: 7921523 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8513. Min Act: -0.1700

Data Index: 4437192 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8493. Min Act: -0.1700

Data Index: 6725710 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8548. Min Act: -0.1700

Data Index: 3395418 (Open Web Text)

Max Activating Token Index: 365

Text #16

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8442. Min Act: -0.1700

Data Index: 5097802 (Open Web Text)

Max Activating Token Index: 974

Text #17

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8590. Min Act: -0.1700

Data Index: 6402831 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8588. Min Act: -0.1700

Data Index: 5369612 (Open Web Text)

Max Activating Token Index: 119

Text #19

Max Range: 4.1687. Min Range: -4.1687

Max Act: 3.8356. Min Act: -0.1700

Data Index: 4226933 (Open Web Text)

Max Activating Token Index: 60